To see the other types of publications on this topic, follow the link: ImageNet Database.
Journal articles on the topic 'ImageNet Database'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'ImageNet Database.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Fei-Fei, L., J. Deng, and K. Li. "ImageNet: Constructing a large-scale image database." Journal of Vision 9, no. 8 (2010): 1037. http://dx.doi.org/10.1167/9.8.1037.
Full text
2
Huang, Yuming. "Multiple SOTA Convolutional Neural Networks for Facial Expression Recognition." Applied and Computational Engineering 8, no. 1 (2023): 240–45. http://dx.doi.org/10.54254/2755-2721/8/20230135.
Full textAbstract:
Facial Expression Recognition (FER) has been a popular topic in the field of computer vision. Various and plentiful facial expression datasets emerged every year for people to train their models and compete. ImageNet, as a massive database for image classification, became a standard benchmark for new computer vision models. Many excellent models such as VGG, ResNet, and EfficientNet managed to excel and were regarded as state-of-the-art models (SOTAs). This study aims to investigate whether SOTA models trained on ImageNet can perform exceptionally well in FER tasks. The models are categorized into three groups based on different weight initialization strategies and then trained and evaluated on the FER-2013 dataset. The results indicate that models with weights trained on ImageNet can be fine-tuned and perform well in FER-2013, particularly when compared to other groups. Finally, simpler models with less computational costs are promoted considering the need for real-time application of facial expression recognition.
3
Sobti, Priyal, Anand Nayyar, Niharika, and Preeti Nagrath. "EnsemV3X: a novel ensembled deep learning architecture for multi-label scene classification." PeerJ Computer Science 7 (May 25, 2021): e557. http://dx.doi.org/10.7717/peerj-cs.557.
Full textAbstract:
Convolutional neural network is widely used to perform the task of image classification, including pretraining, followed by fine-tuning whereby features are adapted to perform the target task, on ImageNet. ImageNet is a large database consisting of 15 million images belonging to 22,000 categories. Images collected from the Web are labeled using Amazon Mechanical Turk crowd-sourcing tool by human labelers. ImageNet is useful for transfer learning because of the sheer volume of its dataset and the number of object classes available. Transfer learning using pretrained models is useful because it helps to build computer vision models in an accurate and inexpensive manner. Models that have been pretrained on substantial datasets are used and repurposed for our requirements. Scene recognition is a widely used application of computer vision in many communities and industries, such as tourism. This study aims to show multilabel scene classification using five architectures, namely, VGG16, VGG19, ResNet50, InceptionV3, and Xception using ImageNet weights available in the Keras library. The performance of different architectures is comprehensively compared in the study. Finally, EnsemV3X is presented in this study. The proposed model with reduced number of parameters is superior to state-of-of-the-art models Inception and Xception because it demonstrates an accuracy of 91%.
4
Manoj krishna, M., M. Neelima, M. Harshali, and M. Venu Gopala Rao. "Image classification using Deep learning." International Journal of Engineering & Technology 7, no. 2.7 (2018): 614. http://dx.doi.org/10.14419/ijet.v7i2.7.10892.
Full textAbstract:
The image classification is a classical problem of image processing, computer vision and machine learning fields. In this paper we study the image classification using deep learning. We use AlexNet architecture with convolutional neural networks for this purpose. Four test images are selected from the ImageNet database for the classification purpose. We cropped the images for various portion areas and conducted experiments. The results show the effectiveness of deep learning based image classification using AlexNet.
5
Varga, Domonkos. "Multi-Pooled Inception Features for No-Reference Image Quality Assessment." Applied Sciences 10, no. 6 (2020): 2186. http://dx.doi.org/10.3390/app10062186.
Full textAbstract:
Image quality assessment (IQA) is an important element of a broad spectrum of applications ranging from automatic video streaming to display technology. Furthermore, the measurement of image quality requires a balanced investigation of image content and features. Our proposed approach extracts visual features by attaching global average pooling (GAP) layers to multiple Inception modules of on an ImageNet database pretrained convolutional neural network (CNN). In contrast to previous methods, we do not take patches from the input image. Instead, the input image is treated as a whole and is run through a pretrained CNN body to extract resolution-independent, multi-level deep features. As a consequence, our method can be easily generalized to any input image size and pretrained CNNs. Thus, we present a detailed parameter study with respect to the CNN base architectures and the effectiveness of different deep features. We demonstrate that our best proposal—called MultiGAP-NRIQA—is able to outperform the state-of-the-art on three benchmark IQA databases. Furthermore, these results were also confirmed in a cross database test using the LIVE In the Wild Image Quality Challenge database.
6
T., Tritva Jyothi Kiran. "Deep Transform Learning Vision Accuracy Analysis on GPU using Tensor Flow." International Journal of Recent Technology and Engineering (IJRTE) 9, no. 3 (2020): 224–27. https://doi.org/10.35940/ijrte.C4402.099320.
Full textAbstract:
Transfer learning is one of the most amazing concepts in machine learning and A.I. Transfer learning is completely unsupervised model. Transfer learning is a machine learning technique in which a network that has been trained to perform a specific task is being reused or repurposed as a starting point to perform another similar task. For this work I used ImageNet Dataset and MobileNet model to analyse Accuracy performance of my Deep Transform learning model on GPU of Intel® Core™ i3-7100U CPU using TensorFlow 2.0 Hub and Keras. ImageNet is an open source Large-Scale dataset of images consisting of 1000 classes and over 1.5 million images. And my overall idea is to analyse accuracy of Vision performance on the very poor network configuration. This work reached an Accuracy almost near to 100% on GPU of Intel® Core™ i3-7100U CPU which is great result with datasets used in this work are not easy to deal and having a lot of classes. That’s why it’s impacting the performance of the network. To classify and predict from tons of images from more classes on low configured network is really challenging one, it’s a great thing the computer vision accuracy showed an excellent vision nearly 100% on GPU in my work.
7
Chen, Yao-Mei, Yenming J. Chen, Yun-Kai Tsai, Wen-Hsien Ho, and Jinn-Tsong Tsai. "Classification of human electrocardiograms by multi-layer convolutional neural network and hyperparameter optimization." Journal of Intelligent & Fuzzy Systems 40, no. 4 (2021): 7883–91. http://dx.doi.org/10.3233/jifs-189610.
Full textAbstract:
A multi-layer convolutional neural network (MCNN) with hyperparameter optimization (HyperMCNN) is proposed for classifying human electrocardiograms (ECGs). For performance tests of the HyperMCNN, ECG recordings for patients with cardiac arrhythmia (ARR), congestive heart failure (CHF), and normal sinus rhythm (NSR) were obtained from three PhysioNet databases: MIT-BIH Arrhythmia Database, BIDMC Congestive Heart Failure Database, and MIT-BIH Normal Sinus Rhythm Database, respectively. The MCNN hyperparameters in convolutional layers included number of filters, filter size, padding, and filter stride. The hyperparameters in max-pooling layers were pooling size and pooling stride. Gradient method was also a hyperparameter used to train the MCNN model. Uniform experimental design approach was used to optimize the hyperparameter combination for the MCNN. In performance tests, the resulting 16-layer CNN with an appropriate hyperparameter combination (16-layer HyperMCNN) was used to distinguish among ARR, CHF, and NSR. The experimental results showed that the average correct rate and standard deviation obtained by the 16-layer HyperMCNN were superior to those obtained by a 16-layer CNN with a hyperparameter combination given by Matlab examples. Furthermore, in terms of performance in distinguishing among ARR, CHF, and NSR, the 16-layer HyperMCNN was superior to the 25-layer AlexNet, which was the neural network that had the best image identification performance in the ImageNet Large Scale Visual Recognition Challenge in 2012.
8
TİRYAKİ, Volkan Müjdat. "Deep Transfer Learning to Classify Mass and Calcification Pathologies from Screen Film Mammograms." Bitlis Eren Üniversitesi Fen Bilimleri Dergisi 12, no. 1 (2023): 57–65. http://dx.doi.org/10.17798/bitlisfen.1190134.
Full textAbstract:
The number of breast cancer diagnosis is the biggest among all cancers, but it can be treated if diagnosed early. Mammography is commonly used for detecting abnormalities and diagnosing the breast cancer. Breast cancer screening and diagnosis are still being performed by radiologists. In the last decade, deep learning was successfully applied on big image classification databases such as ImageNet. Deep learning methods for the automated breast cancer diagnosis is under investigation. In this study, breast cancer mass and calcification pathologies are classified by using deep transfer learning methods. A total of 3,360 patches were used from the Digital Database for Screening Mammography (DDSM) and CBIS-DDSM mammogram databases for convolutional neural network training and testing. Transfer learning was applied using Resnet50, Xception, NASNet, and EfficientNet-B7 network backbones. The best classification performance was achieved by the Xception network. On the original CBIS-DDSM test data, an AUC of 0.9317 was obtained for the five-way classification problem. The results are promising for the implementation of automated diagnosis of breast cancer.
9
Krasteva, Vessela, Todor Stoyanov, Stefan Naydenov, Ramun Schmid, and Irena Jekova. "Detection of Atrial Fibrillation in Holter ECG Recordings by ECHOView Images: A Deep Transfer Learning Study." Diagnostics 15, no. 7 (2025): 865. https://doi.org/10.3390/diagnostics15070865.
Full textAbstract:
Background/Objectives: The timely and accurate detection of atrial fibrillation (AF) is critical from a clinical perspective. Detecting short or transient AF events is challenging in 24–72 h Holter ECG recordings, especially when symptoms are infrequent. This study aims to explore the potential of deep transfer learning with ImageNet deep neural networks (DNNs) to improve the interpretation of short-term ECHOView images for the presence of AF. Methods: Thirty-second ECHOView images, composed of stacked heartbeat amplitudes, were rescaled to fit the input of 18 pretrained ImageNet DNNs with the top layers modified for binary classification (AF, non-AF). Transfer learning provided both retrained DNNs by training only the top layers (513–2048 trainable parameters) and fine-tuned DNNs by slowly training retrained DNNs (0.38–23.48 M parameters). Results: Transfer learning used 13,536 training and 6624 validation samples from the two leads in the IRIDIA-AF Holter ECG database, evenly split between AF and non-AF cases. The top-ranked DNNs evaluated on 11,400 test samples from independent records are the retrained EfficientNetV2B1 (96.3% accuracy with minimal inter-patient (1%) and inter-lead (0.3%) drops), and fine-tuned EfficientNetV2B1 and DenseNet-121, -169, -201 (97.2–97.6% accuracy with inter-patient (1.4–1.6%) and inter-lead (0.5–1.2%) drops). These models can process shorter ECG episodes with a tolerable accuracy drop of up to 0.6% for 20 s and 4–15% for 10 s. Case studies present the GradCAM heatmaps of retrained EfficientNetV2B1 overlaid on raw ECG and ECHOView images to illustrate model interpretability. Conclusions: In an extended deep transfer learning study, we validate that ImageNet DNNs applied to short-term ECHOView images through retraining and fine-tuning can significantly enhance automated AF diagnoses. GradCAM heatmaps provide meaningful model interpretability, highlighting ECG regions of interest aligned with cardiologist focus.
10
Li, Fuqiang, Tongzhuang Zhang, Yong Liu, and Feiqi Long. "Deep Residual Vector Encoding for Vein Recognition." Electronics 11, no. 20 (2022): 3300. http://dx.doi.org/10.3390/electronics11203300.
Full textAbstract:
Vein recognition has been drawing more attention recently because it is highly secure and reliable for practical biometric applications. However, underlying issues such as uneven illumination, low contrast, and sparse patterns with high inter-class similarities make the traditional vein recognition systems based on hand-engineered features unreliable. Recent successes of convolutional neural networks (CNNs) for large-scale image recognition tasks motivate us to replace the traditional hand-engineered features with the superior CNN to design a robust and discriminative vein recognition system. To address the difficulty of direct training or fine-tuning of a CNN with existing small-scale vein databases, a new knowledge transfer approach is formulated using pre-trained CNN models together with a training dataset (e.g., ImageNet) as a robust descriptor generation machine. With the generated deep residual descriptors, a very discriminative model, namely deep residual vector encoding (DRVE), is proposed by a hierarchical design of dictionary learning, coding, and classifier training procedures. Rigorous experiments are conducted with a high-quality hand-dorsa vein database, and superior recognition results compared with state-of-the-art models fully demonstrate the effectiveness of the proposed models. An additional experiment with the PolyU multispectral palmprint database is designed to illustrate the generalization ability.
11
Mohammad, Ahmad Saeed, Thoalfeqar G. Jarullah, Musab T. S. Al-Kaltakchi, Jabir Alshehabi Al-Ani, and Somdip Dey. "IoT-MFaceNet: Internet-of-Things-Based Face Recognition Using MobileNetV2 and FaceNet Deep-Learning Implementations on a Raspberry Pi-400." Journal of Low Power Electronics and Applications 14, no. 3 (2024): 46. http://dx.doi.org/10.3390/jlpea14030046.
Full textAbstract:
IoT applications revolutionize industries by enhancing operations, enabling data-driven decisions, and fostering innovation. This study explores the growing potential of IoT-based facial recognition for mobile devices, a technology rapidly advancing within the interconnected IoT landscape. The investigation proposes a framework called IoT-MFaceNet (Internet-of-Things-based face recognition using MobileNetV2 and FaceNet deep-learning) utilizing pre-existing deep-learning methods, employing the MobileNetV2 and FaceNet algorithms on both ImageNet and FaceNet databases. Additionally, an in-house database is compiled, capturing data from 50 individuals via a web camera and 10 subjects through a smartphone camera. Pre-processing of the in-house database involves face detection using OpenCV’s Haar Cascade, Dlib’s CNN Face Detector, and Mediapipe’s Face. The resulting system demonstrates high accuracy in real-time and operates efficiently on low-powered devices like the Raspberry Pi 400. The evaluation involves the use of the multilayer perceptron (MLP) and support vector machine (SVM) classifiers. The system primarily functions as a closed set identification system within a computer engineering department at the College of Engineering, Mustansiriyah University, Iraq, allowing access exclusively to department staff for the department rapporteur room. The proposed system undergoes successful testing, achieving a maximum accuracy rate of 99.976%.
12
S, Vaishnavi, and Kavitha R. "Multi-Image Concealment in High- Resolution Carriers Using Deep Neural Networks." International Journal of Multidisciplinary Research in Science, Engineering and Technology 7, no. 05 (2024): 10183–90. http://dx.doi.org/10.15680/ijmrset.2024.0705098.
Full textAbstract:
The discipline of concealing a private message within an ordinary public message is referred to as steganography. Over time, steganography has utilized techniques such as LSB manipulation and other simple methods to embed images of lower quality into those of higher quality. Our objective is to employ deep neural networks in the process of concealing and revealing multiple concealed images within a single high-resolution cover image. Deep neural networks are designed to operate in tandem, undergoing simultaneous training to enable both the hiding and revealing procedures. Following training on randomly chosen images from the ImageNet database, the system demonstrates effective performance with authentic photographs from a diverse array of origins.
13
Hassan, Moiz, Kandasamy Illanko, and Xavier N. Fernando. "Single Image Super Resolution Using Deep Residual Learning." AI 5, no. 1 (2024): 426–45. http://dx.doi.org/10.3390/ai5010021.
Full textAbstract:
Single Image Super Resolution (SSIR) is an intriguing research topic in computer vision where the goal is to create high-resolution images from low-resolution ones using innovative techniques. SSIR has numerous applications in fields such as medical/satellite imaging, remote target identification and autonomous vehicles. Compared to interpolation based traditional approaches, deep learning techniques have recently gained attention in SISR due to their superior performance and computational efficiency. This article proposes an Autoencoder based Deep Learning Model for SSIR. The down-sampling part of the Autoencoder mainly uses 3 by 3 convolution and has no subsampling layers. The up-sampling part uses transpose convolution and residual connections from the down sampling part. The model is trained using a subset of the VILRC ImageNet database as well as the RealSR database. Quantitative metrics such as PSNR and SSIM are found to be as high as 76.06 and 0.93 in our testing. We also used qualitative measures such as perceptual quality.
14
Mobark, Nada, Safwat Hamad, and S. Z. Rida. "CoroNet: Deep Neural Network-Based End-to-End Training for Breast Cancer Diagnosis." Applied Sciences 12, no. 14 (2022): 7080. http://dx.doi.org/10.3390/app12147080.
Full textAbstract:
In 2020, according to the publications of both the Global Cancer Observatory (GCO) and the World Health Organization (WHO), breast cancer (BC) represents one of the highest prevalent cancers in women worldwide. Almost 47% of the world’s 100,000 people are diagnosed with breast cancer, among females. Moreover, BC prevails among 38.8% of Egyptian women having cancer. Current deep learning developments have shown the common usage of deep convolutional neural networks (CNNs) for analyzing medical images. Unlike the randomly initialized ones, pre-trained natural image database (ImageNet)-based CNN models may become successfully fine-tuned to obtain improved findings. To conduct the automatic detection of BC by the CBIS-DDSM dataset, a CNN model, namely CoroNet, is proposed. It relies on the Xception architecture, which has been pre-trained on the ImageNet dataset and has been fully trained on whole-image BC according to mammograms. The convolutional design method is used in this paper, since it performs better than the other methods. On the prepared dataset, CoroNet was trained and tested. Experiments show that in a four-class classification, it may attain an overall accuracy of 94.92% (benign mass vs. malignant mass) and (benign calcification vs. malignant calcification). CoroNet has a classification accuracy of 88.67% for the two-class cases (calcifications and masses). The paper concluded that there are promising outcomes that could be improved because more training data are available.
15
León-Paredes, Gabriel Alejandro, Liliana Ibeth Barbosa-Santillán, Juan Jaime Sánchez-Escobar, and Antonio Pareja-Lora. "Ship-SIBISCaS: A First Step towards the Identification of Potential Maritime Law Infringements by means of LSA-Based Image." Scientific Programming 2019 (March 3, 2019): 1–14. http://dx.doi.org/10.1155/2019/1371328.
Full textAbstract:
Maritime safety and security are being constantly jeopardized. Therefore, identifying maritime flow irregularities (semi-)automatically may be crucial to ensure maritime security in the future. This paper presents a Ship Semantic Information-Based, Image Similarity Calculation System (Ship-SIBISCaS), which constitutes a first step towards the automatic identification of this kind of maritime irregularities. In particular, the main goal of Ship-SIBISCaS is to automatically identify the type of ship depicted in a given image (such as abandoned, cargo, container, hospital, passenger, pirate, submersible, three-decker, or warship) and, thus, classify it accordingly. This classification is achieved in Ship-SIBISCaS by finding out the similarity of the ship image and/or description with other ship images and descriptions included in its knowledge base. This similarity is calculated by means of an LSA algorithm implementation that is run on a parallel architecture consisting of CPUs and GPUs (i.e., a heterogeneous system). This implementation of the LSA algorithm has been trained with a collection of texts, extracted from Wikipedia, that associate some semantic information to ImageNet ship images. Thanks to its parallel architecture, the indexing process of this image retrieval system has been accelerated 10 times (for the 1261 ships included in ImageNet). The range of the precision of the image similarity method is 46% to 92% with 100% recall (that is, a 100% coverage of the database).
16
Gomez-Zuleta, Martin Alonso, Iego Fernando Cano-Rosales, Diego Fernando Bravo-Higuera, Josue Andre Ruano-Balseca, and Eduardo Romero-Castro. "Application of Artificial Intelligence Technology in Automatic Detec-tion of large Intestine Polyps." Journal of Autonomous Intelligence 4, no. 2 (2021): 72. http://dx.doi.org/10.32629/jai.v4i2.503.
Full textAbstract:
<div><p class="4"><strong>Objective:</strong> to establish an automatic colonoscopy method based on artificial intelligence. <strong>Methods:</strong> a public database established by a university hospital was used, including colorectal fat and data collection. Initially, all frames in the video are normalized to reduce the high variability between databases. Then, the convolution neural network is used for full depth learning to complete the detection task of polyps. The network starts with the weights learned from millions of natural images in the ImageNet database. According to the fine-tuning technology, the colonoscopy image is used to update the network weight. Finally, the detection of polyps is performed by assigning the probability of containing Po ́ lipo to each table and determining the threshold defined when polyps appears in the table. <strong>Results:</strong> 1875 cases were collected from 5 public databases and databases established by university hospitals, with a total of 123046 forms. The method was trained and evaluated. Comparing the results with the scores of different colonoscopy experts, the accuracy was 0.77, the sensitivity was 0.89, the specificity was 0.71, and the ROC curve (re ceiver operation characteristics) was 0.87. <strong>Conclusion:</strong> compared with experienced gastrointestinal markers, this method overcomes the high variability of different types of lesions and different colonic light conditions (handle, folding or contraction), has very high sensitivity, and can reduce human errors, which is one of the main factors leading to the non detection or leakage of Po lipids in colonoscopy.</p></div>
17
Mabrouk, Alhassan, Rebeca P. Díaz Redondo, Abdelghani Dahou, Mohamed Abd Elaziz, and Mohammed Kayed. "Pneumonia Detection on Chest X-ray Images Using Ensemble of Deep Convolutional Neural Networks." Applied Sciences 12, no. 13 (2022): 6448. http://dx.doi.org/10.3390/app12136448.
Full textAbstract:
Pneumonia is a life-threatening lung infection resulting from several different viral infections. Identifying and treating pneumonia on chest X-ray images can be difficult due to its similarity to other pulmonary diseases. Thus, the existing methods for predicting pneumonia cannot attain substantial levels of accuracy. This paper presents a computer-aided classification of pneumonia, coined Ensemble Learning (EL), to simplify the diagnosis process on chest X-ray images. Our proposal is based on Convolutional Neural Network (CNN) models , which are pretrained CNN models that have been recently employed to enhance the performance of many medical tasks instead of training CNN models from scratch. We propose to use three well-known CNNs (DenseNet169, MobileNetV2, and Vision Transformer) pretrained using the ImageNet database.
18
Bi, Ning, Jiahao Chen, and Jun Tan. "The Handwritten Chinese Character Recognition Uses Convolutional Neural Networks with the GoogLeNet." International Journal of Pattern Recognition and Artificial Intelligence 33, no. 11 (2019): 1940016. http://dx.doi.org/10.1142/s0218001419400160.
Full textAbstract:
With the outstanding performance in 2014 at the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14), an effective convolutional neural network (CNN) model named GoogLeNet has drawn the attention of the mainstream machine learning field. In this paper we plan to take an insight into the application of the GoogLeNet in the Handwritten Chinese Character Recognition (HCCR) on the database HCL2000 and CASIA-HWDB with several necessary adjustments and also state-of-the-art improvement methods for this end-to-end approach. Through the experiments we have found that the application of the GoogLeNet for the Handwritten Chinese Character Recognition (HCCR) results into significant high accuracy, to be specific more than 99% for the final version, which is encouraging for us to further research.
19
Schott, Sandro Minarrine Cotrim, Marcones Cleber Brito da Silva, Delvonei Alves de Andrade, and Roberto Navarro de Mesquita. "Convolutional neural network-based pattern recognition in natural circulation instability images." Concilium 24, no. 4 (2024): 267–88. http://dx.doi.org/10.53660/clm-2919-24d10.
Full textAbstract:
Heat removal systems employing natural circulation are key in new nuclear power plant designs for mitigating accidents. This study applies Convolutional Neural Networks (CNNs) to classify 'chugging' instability phases, analyzing 1152 two-phase flow images from a Natural Circulation Circuit. Three CNN models, including one incorporating transfer learning from the ImageNet database, were trained via five-fold cross-validation to fine-tune hyperparameters. This involved comparing models with and without transfer learning against a baseline linear model. A model using a pre-trained Resnet50 with transfer learning accurately classified all 230 samples, outperforming the baseline linear model with an F1-Score of 0.859. The results endorse the use of CNNs with transfer learning for thermohydraulic image analysis in identifying natural circulation instability stages.
20
Ayana, Gelan, Jinhyung Park, and Se-woon Choe. "Patchless Multi-Stage Transfer Learning for Improved Mammographic Breast Mass Classification." Cancers 14, no. 5 (2022): 1280. http://dx.doi.org/10.3390/cancers14051280.
Full textAbstract:
Despite great achievements in classifying mammographic breast-mass images via deep-learning (DL), obtaining large amounts of training data and ensuring generalizations across different datasets with robust and well-optimized algorithms remain a challenge. ImageNet-based transfer learning (TL) and patch classifiers have been utilized to address these challenges. However, researchers have been unable to achieve the desired performance for DL to be used as a standalone tool. In this study, we propose a novel multi-stage TL from ImageNet and cancer cell line image pre-trained models to classify mammographic breast masses as either benign or malignant. We trained our model on three public datasets: Digital Database for Screening Mammography (DDSM), INbreast, and Mammographic Image Analysis Society (MIAS). In addition, a mixed dataset of the images from these three datasets was used to train the model. We obtained an average five-fold cross validation AUC of 1, 0.9994, 0.9993, and 0.9998 for DDSM, INbreast, MIAS, and mixed datasets, respectively. Moreover, the observed performance improvement using our method against the patch-based method was statistically significant, with a p-value of 0.0029. Furthermore, our patchless approach performed better than patch- and whole image-based methods, improving test accuracy by 8% (91.41% vs. 99.34%), tested on the INbreast dataset. The proposed method is of significant importance in solving the need for a large training dataset as well as reducing the computational burden in training and implementing the mammography-based deep-learning models for early diagnosis of breast cancer.
21
Gómez-Zuleta, Martín Alonso, Diego Fernando Cano-Rosales, Diego Fernando Bravo-Higuera, Josué André Ruano-Balseca, and Eduardo Romero-Castro. "Automatic detection of colorectal polyps using artificial intelligence techniques." Metaverse 2, no. 1 (2021): 11. http://dx.doi.org/10.54517/m.v2i1.1793.
Full textAbstract:
<p>Colorectal cancer (CRC) is one of the most prevalent malignant tumors in Colombia and the world. These neoplasms originate in adenomatous lesions or polyps that must be resected to prevent the disease, which can be done with a colonoscopy. It has been reported that during colonoscopy polyps are detected in 40% of men and 30% of women (hyperplastic, adenomatous, serrated, among others), and, on average, 25% of adenomatous polyps (main quality indicator in colonoscopy). However, these lesions are not easy to observe due to the multiplicity of blind spots in the colon and the human error associated with the examination. Objective: to create a computational method for the automatic detection of colorectal polyps using artificial intelligence in recorded videos of real colonoscopy procedures. Methodology: public databases with colorectal polyps and a data collection built in a University Hospital were used. Initially, all the frames of the videos were normalized to reduce the high variability between databases. Subsequently, the polyp detection task is done with a deep learning method using a convolutional neural network. This network is initialized with weights learned on millions of national images from the ImageNet database. The weights of the network are updated using colonoscopy images, following the tuning technique. <strong></strong></p>
22
Gómez-Zuleta, Martín Alonso, Diego Fernando Cano-Rosales, Diego Fernando Bravo-Higuera, Josué André Ruano-Balseca, and Eduardo Romero-Castro. "Automatic detection of colorectal polyps using artificial intelligence techniques." Metaverse 2, no. 1 (2021): 11. http://dx.doi.org/10.54517/met.v2i1.1793.
Full textAbstract:
<p>Colorectal cancer (CRC) is one of the most prevalent malignant tumors in Colombia and the world. These neoplasms originate in adenomatous lesions or polyps that must be resected to prevent the disease, which can be done with a colonoscopy. It has been reported that during colonoscopy polyps are detected in 40% of men and 30% of women (hyperplastic, adenomatous, serrated, among others), and, on average, 25% of adenomatous polyps (main quality indicator in colonoscopy). However, these lesions are not easy to observe due to the multiplicity of blind spots in the colon and the human error associated with the examination. Objective: to create a computational method for the automatic detection of colorectal polyps using artificial intelligence in recorded videos of real colonoscopy procedures. Methodology: public databases with colorectal polyps and a data collection built in a University Hospital were used. Initially, all the frames of the videos were normalized to reduce the high variability between databases. Subsequently, the polyp detection task is done with a deep learning method using a convolutional neural network. This network is initialized with weights learned on millions of national images from the ImageNet database. The weights of the network are updated using colonoscopy images, following the tuning technique. <strong></strong></p>
23
Laazoufi, Abdelouahed, Mohammed El Hassouni, and Hocine Cherifi. "Point Cloud Quality Assessment Using a One-Dimensional Model Based on the Convolutional Neural Network." Journal of Imaging 10, no. 6 (2024): 129. http://dx.doi.org/10.3390/jimaging10060129.
Full textAbstract:
Recent advancements in 3D modeling have revolutionized various fields, including virtual reality, computer-aided diagnosis, and architectural design, emphasizing the importance of accurate quality assessment for 3D point clouds. As these models undergo operations such as simplification and compression, introducing distortions can significantly impact their visual quality. There is a growing need for reliable and efficient objective quality evaluation methods to address this challenge. In this context, this paper introduces a novel methodology to assess the quality of 3D point clouds using a deep learning-based no-reference (NR) method. First, it extracts geometric and perceptual attributes from distorted point clouds and represent them as a set of 1D vectors. Then, transfer learning is applied to obtain high-level features using a 1D convolutional neural network (1D CNN) adapted from 2D CNN models through weight conversion from ImageNet. Finally, quality scores are predicted through regression utilizing fully connected layers. The effectiveness of the proposed approach is evaluated across diverse datasets, including the Colored Point Cloud Quality Assessment Database (SJTU_PCQA), the Waterloo Point Cloud Assessment Database (WPC), and the Colored Point Cloud Quality Assessment Database featured at ICIP2020. The outcomes reveal superior performance compared to several competing methodologies, as evidenced by enhanced correlation with average opinion scores.
24
Lin, Weipeng. "Research on Volleyball Image Classification Based on Artificial Intelligence and SIFT Algorithm." Mathematical Problems in Engineering 2021 (March 20, 2021): 1–10. http://dx.doi.org/10.1155/2021/5547689.
Full textAbstract:
Due to the application scenarios of image matching, different scenarios have different requirements for matching performance. Faced with this situation, people cannot accurately and timely find the information they need. Therefore, the research of image classification technology is very important. Image classification technology is one of the important research directions of computer vision and pattern recognition, but there are still few researches on volleyball image classification. The selected databases are the general database ImageNet library and COCO library. First, the color image is converted into a gray image through gray scale transformation, and then the scale space theory is integrated into the image feature point extraction process through the SIFT algorithm. Extract local feature points from the volleyball image, and then combine them with the Random Sample Consensus (RANSAC) algorithm to eliminate the resulting mismatch. Analyze the characteristic data to obtain the data that best reflects the image characteristics, and use the data to classify existing volleyball images. The algorithm can effectively reduce the amount of data and has high classification performance. It aims to improve the accuracy of image matching or reduce the time cost. This research has very important use value in practical applications.
25
Chen, Mo. "A Comparative Study of Transfer Learning based Models for Lung Cancer Histopathology Classification." Highlights in Science, Engineering and Technology 39 (April 1, 2023): 26–34. http://dx.doi.org/10.54097/hset.v39i.6488.
Full textAbstract:
Lung cancer is the deadliest form of cancer, which attracted a lot of attention in the past. Transfer learning is a very popular approach in deep learning as it can apply the knowledge obtained from a previous task to improve the performance in another. In this research, four transfer learning models with different complexity are utilized to detect lung cancer, which are AlexNet, VGG16, ResNet50 and Inception-v3. Since the early detection and histopathological diagnosis can considerably decrease the likelihood of mortality, the lung cancer histopathological images dataset is considered. This dataset contains histopathological images of 3 classes, all of them are considered in this study. Firstly, the four models are trained on the histopathological database from random initialization for 10 epochs. Next, the four models are first pre-trained on ImageNet and then trained on the histopathological dataset for 10 epochs. For each epoch, the testing accuracy is recorded so as to find the optimal number of epochs and determine whether transfer learning models are capable in lung cancer detection. Then, various evaluation metrics e.g., accuracy and precision are used to measure and compare the four models’ performance. The study’s finding shows that AlexNet, VGG16, ResNet50 and Inception-v3 pre-trained on ImageNet are adequate in lung cancer detection. There corresponding accuracy rates are 99.367%, 99.800%, 100% and 100% respectively, which are much higher than that trained from random initialization. Among the four transfer learning models, ResNet50 and Inception-v3 perform the best on lung cancer classification.
26
Zhao, Zepeng. "A comparative study of large-scale and lightweight convolutional neural networks for ImageNet classification." Applied and Computational Engineering 47, no. 1 (2024): 101–10. http://dx.doi.org/10.54254/2755-2721/47/20241236.
Full textAbstract:
In the field of convolution neural networks (CNNs), many impressive architectures have been published in recent years. These can be roughly divided into two groups: large-scale models and lightweight models. These large models are characterized by many trainable weights and complex network structures, offering them strong effectiveness in various computer vision tasks, and have become essential components of many modern visual recognition systems. These lightweight CNNs are designed to maintain high performance with limited memory and computational resources. They are highly efficient in terms of inference time and resource utilization, so that particularly suitable for mobile and edge computing devices. This work focuses on some prominent models based on the ImageNet database and explores the reasons for their frameworks success. By analyzing these models, a trend could be identified in the development of CNN models: Reasonably increasing the scale of the model and utilizing suitable frameworks can both improve accuracy and efficiency.
27
M., Sandeep Reddy, Chinmai Ch., Sai Teja B., and M. Ashok Kumar P. "Facial Expression Detection using Deep Neural Networks." International Journal of Engineering and Advanced Technology (IJEAT) 9, no. 3 (2020): 1318–20. https://doi.org/10.35940/ijeat.C5340.029320.
Full textAbstract:
Facial Expression conveys nonverbal communication, which plays an important role in acquaintance among people. The facial expression detection system is an activity to identify the emotional state of the person. In this system, a captured frame is compared with trained data set that is available in the database and then state of the captured frame is defined. This system is based on Image Processing and Machine Learning. For designing a robust facial feature descriptor, we apply the Xception Modelling algorithm. The detection performance of the proposed method will be evaluated by loading the dataset and pre-processing the images for feeding it to CNN model. Experimental results with prototypic expressions show the superiority of the Xception-Model descriptor against some well-known appearance-based feature representation methods. Experimental results demonstrate the competitive classification accuracy for our proposed method.
28
Shah, Ansar Munir, and Itrat Abid. "Dynamic and Integrated Security Model in Inter Cloud for Image Classification." Foundation University Journal of Engineering and Applied Sciences <br><i style="color:black;">(HEC Recognized Y Category , ISSN 2706-7351)</i> 4, no. 1 (2024): 61–69. http://dx.doi.org/10.33897/fujeas.v4i1.874.
Full textAbstract:
Cloud computing has transformed software and database accessibility, utilizing the Internet and server hosting. However, security risks arise, including malware attacks and website hacking. To address these challenges, deep learning models like ResNet50 have been developed. Trained on encrypted images, ResNet50 enhances the speed and accuracy of image recognition, enabling the identification of hidden data without decryption. Despite inter-cloud communication issues, cloud servers prioritize data security, user privacy, and integrity maintenance. The ResNet50 model exhibits impressive performance, achieving 99.5%accuracy and precision-recall scores of 99.5% and 99.5% using the ImageNet Dataset. Cloud computing offers significant advantages, but data security remains a critical concern. Encrypted image recognition powered by deep learning models offers efficient and private solutions. Cloud providers continually strive to improve inter-cloud communication, ensuring comprehensive protection for data and system integrity. The remarkable capabilities of ResNet50 highlight its potential in encrypted image analysis tasks.
29
Boukhari, Djamel Eddine. "Facial Beauty Prediction Based on Vision Transformer." International Journal of Electrical and Electronic Engineering & Telecommunications 13, no. 3 (2024): 252–59. http://dx.doi.org/10.18178/ijeetc.13.3.252-259.
Full textAbstract:
Facial beauty analysis is a crucial subject in human culture among researchers across various applications. Recent studies have utilized multidisciplinary approaches to examine the relationship between facial traits, age, emotions, and other factors. Facial beauty prediction is a significant visual recognition challenge that evaluates facial attractiveness for human perception. This task demands considerable effort due to the novelty of the field and the limited resources available, including a small database for facial beauty prediction. In this context, a deep learning method has recently shown remarkable capabilities in predicting facial beauty. Additionally, vision Transformers have recently been introduced as novel deep learning approaches and have shown strong performance in various applications. The key issue is that the vision transformer performs significantly worse than ResNet when trained on a small ImageNet database. In this paper, we propose to address the challenges of predicting facial beauty by utilizing vision transformers instead of relying on feature extraction based on Convolutional Neural Networks, which are commonly used in traditional methods. Moreover, we define and optimize a set of hyperparameters according to the SCUT-FBP5500 benchmark dataset. The model achieves a Pearson coefficient of 0.9534. Experimental results indicated that using this proposed network leads to better predicting facial beauty closer to human evaluation than conventional technology that provides facial beauty assessment.
30
Ramasamy, Meena Prakash, Thayammal Subburaj, Valarmathi Krishnasamy, and Vimala Mannarsamy. "Performance analysis of breast cancer histopathology image classification using transfer learning models." International Journal of Electrical and Computer Engineering (IJECE) 14, no. 5 (2024): 6006. http://dx.doi.org/10.11591/ijece.v14i5.pp6006-6015.
Full textAbstract:
Convolutional neural networks (CNN) which are deep learning-based methods are being currently successfully deployed and have gained much popularity in medical image analysis. CNN can handle enormous amounts of medical data which makes it possible for accurate detection and classification of breast cancer from histopathological images. In the proposed method, we have implemented transfer learning-based classification of breast cancer histopathological images using DenseNet121, DenseNet201, VGG16, VGG19, InceptionV3, and MobileNetV2 and made a performance analysis of the different models on the publicly available dataset of BreakHis. These networks were pre-trained on the ImageNet database and initialized with weights which are fine-tuned by training with input histopathological images. These models are trained with images of the BreakHis dataset with multiple image magnifications. From the comparative study of these pre-trained models on histopathology images, it is inferred that DenseNet121 achieves the highest breast cancer classification accuracy of 0.965 compared to other models and contemporary methods.
31
Wang, Jian, Haisen Li, Guanying Huo, Chao Li, and Yuhang Wei. "Multi-Mode Channel Position Attention Fusion Side-Scan Sonar Transfer Recognition." Electronics 12, no. 4 (2023): 791. http://dx.doi.org/10.3390/electronics12040791.
Full textAbstract:
Side-scan sonar (SSS) target recognition is an important part of building an underwater detection system and ensuring a high-precision perception of underwater information. In this paper, a novel multi-channel multi-location attention mechanism is proposed for a multi-modal phased transfer side-scan sonar target recognition model. Optical images from the ImageNet database, synthetic aperture radar (SAR) images and SSS images are used as the training datasets. The backbone network for feature extraction is transferred and learned by a staged transfer learning method. The head network used to predict the type of target extracts the attention features of SSS through a multi-channel and multi-position attention mechanism, and subsequently performs target recognition. The proposed model is tested on the SSS test dataset and evaluated using several metrics, and compared with different recognition algorithms as well. The results show that the model has better recognition accuracy and robustness for SSS targets.
32
Shonkoff, Eleanor, Kelly Copeland Cara, Xuechen (Anna) Pei, et al. "The State of the Science on Artificial Intelligence-Based Dietary Assessment Methods That Use Digital Images: A Scoping Review." Current Developments in Nutrition 6, Supplement_1 (2022): 534. http://dx.doi.org/10.1093/cdn/nzac077.037.
Full textAbstract:
Abstract Objectives Human error when estimating food intake is a major source of bias in nutrition research. This study provides an overview of literature on the accuracy of artificial intelligence (AI) methods used to analyze digital images of food compared to human coders and ground truth. Methods This scoping review included peer-reviewed journal articles reporting AI (e.g., deep learning) and image coding for food analysis. Literature was searched through August 2021 in 4 databases plus reference mining in conference papers and reviews. Eligible articles reported volume, energy, or nutrients estimated from digital food images via fully automatic AI methods. Two investigators independently screened and extracted data. Study characteristics, methods, and type of results were extracted. Results In total, 8,761 unique publications were identified; 35 papers published from 2010 to 2021 (77% after 2015) were included. Preliminary results are reported. Most papers used newly-captured images or created a digital image database (77%). Some used named image databases (e.g., Rakuten18, UEC Food-100); only ImageNet and Inselspital's dataset were used in more than one study. Most (63%) reported relying on a nutrient database to derive nutrient values; 31% specified using USDA FoodData Central databases. The most frequently reported estimation accuracy results were absolute error (AE; 46%), relative error (RE; 40%), correlation coefficient (26%), and error rate (23%). Other reported measures were Bland-Altman plots; actual and estimated values (e.g., volumes, nutrients); and tests of mean differences. Results were reported for calories (AE, 26% of all studies; RE 20%); macronutrients (AE 20%, RE 9%); volume, mass, weight, or area (AE 17%; RE 26%); and salt (AE 6%; RE 6%). Conclusions Significant resources have been devoted to investigating the ability of AI methods to conduct accurate dietary assessment using digital food images. Yet, substantial variability in the databases used and results reported prevents quantitative synthesis of overall accuracy across studies. A validated risk of bias tool is needed to compare study quality. Future research should consider using a limited number of valid databases for food images and nutrition information, and reports should at least include absolute and relative error for volume estimations. Funding Sources Supported by an NIH grant.
33
Hasan, et. al., Haitham S. "EEG-based image classification using an efficient geometric deep network based on functional connectivity." Periodicals of Engineering and Natural Sciences (PEN) 11, no. 1 (2025): 208–15. https://doi.org/10.21533/pen.v11.i1.90.
Full textAbstract:
To ensure that the FC-GDN is properly calibrated for the EEG-ImageNet dataset, we subject it to extensive training and gather all of the relevant weights for its parameters. Making use of the FC-GDN pseudo-code. The dataset is split into a "train" and "test" section in Kfold cross-validation. Ten-fold recommends using ten folds, with one fold being selected as the test split at each iteration. This divides the dataset into 90% training data and 10% test data. In order to train all 10 folds without overfitting, it is necessary to apply this procedure repeatedly throughout the whole dataset. Each training fold is arrived at after several iterations. After training all ten folds, results are analyzed. For each iteration, the FC-GDN weights are optimized by the SGD and ADAM optimizers. The ideal network design parameters are based on the convergence of the trains and the precision of the tests. This study offers a novel geometric deep learning-based network architecture for classifying visual stimulation categories using electroencephalogram (EEG) data from human participants while they watched various sorts of images. The primary goals of this study are to (1) eliminate feature extraction from GDL-based approaches and (2) extract brain states via functional connectivity. Tests with the EEG-ImageNet database validate the suggested method's efficacy. FC-GDN is more efficient than other cutting-edge approaches for boosting classification accuracy, requiring fewer iterations. In computational neuroscience, neural decoding addresses the problem of mind-reading. Because of its simplicity of use and temporal precision, Electroencephalographys (EEG) are commonly employed to monitor brain activity. Deep neural networks provide a variety of ways to detecting brain activity. Using a Function Connectivity (FC) - Geometric Deep Network (GDN) and EEG channel functional connectivity, this work directly recovers hidden states from high-resolution temporal data. The time samples taken from each channel are utilized to represent graph signals on a topological connection network based on EEG channel functional connectivity. A novel graph neural network architecture evaluates users' visual perception state utilizing extracted EEG patterns associated to various picture categories using graphically rendered EEG recordings as training data. The efficient graph representation of EEG signals serves as the foundation for this design. Proposal for an FC-GDN EEG-ImageNet test. Each category has a maximum of 50 samples. Nine separate EEG recorders were used to obtain these images. The FC-GDN approach yields 99.4% accuracy, which is 0.1% higher than the most sophisticated method presently available
34
-Rehman, Aziz-ur, Nabeel Ali, Imtiaz A. Taj, Muhammad Sajid, and Khasan S. Karimov. "An Automatic Mass Screening System for Cervical Cancer Detection Based on Convolutional Neural Network." Mathematical Problems in Engineering 2020 (October 28, 2020): 1–14. http://dx.doi.org/10.1155/2020/4864835.
Full textAbstract:
Cervical cancer is the fourth most common type of cancer and is also a leading cause of mortality among women across the world. Various types of screening tests are used for its diagnosis, but the most popular one is the Papanicolaou smear test, in which cell cytology is carried out. It is a reliable tool for early identification of cervical cancer, but there is always a chance of misdiagnosis because of possible errors in human observations. In this paper, an auto-assisted cervical cancer screening system is proposed that uses a convolutional neural network trained on Cervical Cells database. The training of the network is accomplished through transfer learning, whereby initializing weights are obtained from the training on ImageNet dataset. After fine-tuning the network on the Cervical Cells database, the feature vector is extracted from the last fully connected layer of convolutional neural network. For final classification/screening of the cell samples, three different classifiers are proposed including Softmax regression (SR), Support vector machine (SVM), and GentleBoost ensemble of decision trees (GEDT). The performance of the proposed screening system is evaluated for two different testing protocols, namely, 2-class problem and 7-class problem, on the Herlev database. Classification accuracies of SR, SVM, and GEDT for the 2-class problem are found to be 98.8%, 99.5%, and 99.6%, respectively, while for the 7-class problem, they are 97.21%, 98.12%, and 98.85%, respectively. These results show that the proposed system provides better performance than its previous counterparts under various testing conditions.
35
Osmani, Nooshin, Sorayya Rezayi, Erfan Esmaeeli, and Afsaneh Karimi. "Transfer Learning from Non-Medical Images to Medical Images Using Deep Learning Algorithms." Frontiers in Health Informatics 13 (January 6, 2024): 177. http://dx.doi.org/10.30699/fhi.v13i0.549.
Full textAbstract:
Introduction: Machine learning, especially deep convolutional neural networks (DCNNs), is a popular method for computerizing medical image analysis. This study aimed to develop DCNN models for histopathology image classification utilizing transfer learning.Material and Methods: We utilized 16 different pre-trained DCNNs to analyze the histopathology images from the animal diagnostic laboratory (ADL) database. During the image preprocessing stage, we applied two methods. The first method involved subtracting the mean of ImageNet images from all images. The second method involved subtracting the mean of histopathology training images from all images. Next, in the 16 pre-trained networks, feature extraction was done from their final six layers, and the features extracted from each layer were fed separately into the linear and non-linear support vector machine (SVM) for classification.Results: The results obtained from the ADL database show that the classification rate in lung tissue images is much better than that of the kidney and spleen. For example, the lowest detection rate in non-linear SVM for lung tissue is 14.96%, almost close to the highest accuracy in kidney and spleen tissue. The classification accuracy of the spleen images is better than that of the kidneys, with only a slight difference. In linear SVM on lung images, ResNet101 obtained the most accurate result with a value of 99.56%, followed by ResNet50, ResNet152, VGG_16, and VGG_19. In non-linear SVM on lung tissue images, the ResNet101 network with 99.65% and ResNet50 with 99.21%, followed by ResNet152, VGG_16, and VGG_19 obtained the highest detection rate.Conclusion: The classification results obtained from different methods on the ADL (including kidney, spleen, and lung histopathology images) database, confirmed the validity of transferring knowledge between non-medical and medical histopathology images. Additionally, it demonstrates the success of combining classifiers trained on deep features. This research obtained higher accuracy in the ADL database than the works done.
36
Erokhin, V. V. "GREEDY LAYERBYLAYER LEARNING OF CONVOLUTIONAL NEURAL NETWORKS." SOFT MEASUREMENTS AND COMPUTING 1, no. 11 (2021): 66–83. http://dx.doi.org/10.36871/2618-9976.2021.11.004.
Full textAbstract:
Layer-by-layer training is an alternative end-to-end backpropagation approach for training deep convolutional neural networks. Layer-by-layer training on specific architectures can yield very competitive results. In the ImageNet database (www.imagenet. org), layer-by-layer trained networks can perform comparable to many modern end-to-end trained networks. This article compares the performance gap between the two training procedures over a wide range of network architectures and further analyzes the potential limitations of layer-by-layer training. The results show that layer-by-layer learning quickly saturates after a certain critical level due to overfitting of early levels in neural networks. Several approaches that have been used to solve this problem are discussed, and a methodology for improving layer-by-layer learning in various neural network architectures is discussed. Fundamentally, this research highlights the need to open up the black box that represents modern deep neural networks and explore the layer-by-layer interactions between intermediate hidden layers within deep networks through the lens of layer-by-layer learning.
37
Awang Iskandar, Dayang N. F., Albert A. Zijlstra, Iain McDonald, et al. "Classification of Planetary Nebulae through Deep Transfer Learning." Galaxies 8, no. 4 (2020): 88. http://dx.doi.org/10.3390/galaxies8040088.
Full textAbstract:
This study investigate the effectiveness of using Deep Learning (DL) for the classification of planetary nebulae (PNe). It focusses on distinguishing PNe from other types of objects, as well as their morphological classification. We adopted the deep transfer learning approach using three ImageNet pre-trained algorithms. This study was conducted using images from the Hong Kong/Australian Astronomical Observatory/Strasbourg Observatory H-alpha Planetary Nebula research platform database (HASH DB) and the Panoramic Survey Telescope and Rapid Response System (Pan-STARRS). We found that the algorithm has high success in distinguishing True PNe from other types of objects even without any parameter tuning. The Matthews correlation coefficient is 0.9. Our analysis shows that DenseNet201 is the most effective DL algorithm. For the morphological classification, we found for three classes, Bipolar, Elliptical and Round, half of objects are correctly classified. Further improvement may require more data and/or training. We discuss the trade-offs and potential avenues for future work and conclude that deep transfer learning can be utilized to classify wide-field astronomical images.
38
Chen, Zenghai, Hong Fu, Wai-Lun Lo, and Zheru Chi. "Strabismus Recognition Using Eye-Tracking Data and Convolutional Neural Networks." Journal of Healthcare Engineering 2018 (2018): 1–9. http://dx.doi.org/10.1155/2018/7692198.
Full textAbstract:
Strabismus is one of the most common vision diseases that would cause amblyopia and even permanent vision loss. Timely diagnosis is crucial for well treating strabismus. In contrast to manual diagnosis, automatic recognition can significantly reduce labor cost and increase diagnosis efficiency. In this paper, we propose to recognize strabismus using eye-tracking data and convolutional neural networks. In particular, an eye tracker is first exploited to record a subject’s eye movements. A gaze deviation (GaDe) image is then proposed to characterize the subject’s eye-tracking data according to the accuracies of gaze points. The GaDe image is fed to a convolutional neural network (CNN) that has been trained on a large image database called ImageNet. The outputs of the full connection layers of the CNN are used as the GaDe image’s features for strabismus recognition. A dataset containing eye-tracking data of both strabismic subjects and normal subjects is established for experiments. Experimental results demonstrate that the natural image features can be well transferred to represent eye-tracking data, and strabismus can be effectively recognized by our proposed method.
39
Satybaldina, Dina, and Gulzia Kalymova. "Deep learning based static hand gesture recognition." Indonesian Journal of Electrical Engineering and Computer Science 21, no. 1 (2021): 398. http://dx.doi.org/10.11591/ijeecs.v21.i1.pp398-405.
Full textAbstract:
Hand gesture recognition becomes a popular topic of deep learning and provides many application fields for bridging the human–computer barrier and has a positive impact on our daily life. The primary idea of our project is a static gesture acquisition from depth camera and to process the input images to train the deep convolutional neural network pre-trained on ImageNet dataset. Proposed system consists of gesture capture device (Intel® RealSense™ depth camera D435), pre-processing and image segmentation algorithms, feature extraction algorithm and object classification. For pre-processing and image segmentation algorithms computer vision methods from the OpenCV and Intel Real Sense libraries are used. The subsystem for features extracting and gestures classification is based on the modified VGG-16 by using the TensorFlow&amp;Keras deep learning framework. Performance of the static gestures recognition system is evaluated using maching learning metrics. Experimental results show that the proposed model, trained on a database of 2000 images, provides high recognition accuracy both at the training and testing stages.
40
Le Thi Thu Hong, Nguyen Sinh Huy, Nguyen Duc Hanh, et al. "Polyp segmentation on colonoscopy image using improved Unet and transfer learning." Journal of Military Science and Technology, CSCE6 (December 30, 2022): 41–55. http://dx.doi.org/10.54939/1859-1043.j.mst.csce6.2022.41-55.
Full textAbstract:
Colorectal cancer is among the most common malignancies and can develop from high-risk colon polyps. Colonoscopy remains the gold-standard investigation for colorectal cancer screening. The procedure could benefit greatly from using AI models for automatic polyp segmentation, which provide valuable insights for improving colon polyp dection. Additionally, it will support gastroenterologists during image analysation to correctly choose the treatment with less time. In this paper, the framework of polyp image segmentation is developed by a deep learning approach, especially a convolutional neural network. The proposed framework is based on improved Unet architecture to obtain the segmented polyp image. We also propose to use the transfer learning method to transfer the knowledge learned from the ImageNet general image dataset to the endoscopic image field. This framework used the Kvasir-SEG database, which contains 1000 GI polyp images and corresponding segmentation masks according to annotation by medical experts. The results confirmed that our proposed method outperform the state-of-the-art polyp segmentation methods with 94.79% dice, 90.08% IOU, 98.68% recall, and 92.07% precision.
41
Satybaldina, Dina, and Gulzia Kalymova. "Deep learning based static hand gesture recognition." Indonesian Journal of Electrical Engineering and Computer Science 21, no. 1 (2021): 398–405. https://doi.org/10.11591/ijeecs.v21.i1.pp398-405.
Full textAbstract:
Hand gesture recognition becomes a popular topic of deep learning and provides many application fields for bridging the human-computer barrier and has a positive impact on our daily life. The primary idea of our project is a static gesture acquisition from depth camera and to process the input images to train the deep convolutional neural network pre-trained on ImageNet dataset. Proposed system consists of gesture capture device (Intel® RealSense™ depth camera D435), pre-processing and image segmentation algorithms, feature extraction algorithm and object classification. For preprocessing and image segmentation algorithms computer vision methods from the OpenCV and Intel Real Sense libraries are used. The subsystem for features extracting and gestures classification is based on the modified VGG16 by using the TensorFlow&Keras deep learning framework. Performance of the static gestures recognition system is evaluated using maching learning metrics. Experimental results show that the proposed model, trained on a database of 2000 images, provides high recognition accuracy both at the training and testing stages.
42
Лихотин, М. А. "USE OF CONVOLUTIONAL NEURAL NETWORKS FOR PREDICTION OF BRAIN TUMORS." ВЕСТНИК ВОРОНЕЖСКОГО ГОСУДАРСТВЕННОГО ТЕХНИЧЕСКОГО УНИВЕРСИТЕТА, no. 2 (May 5, 2023): 27–32. http://dx.doi.org/10.36622/vstu.2023.19.2.004.
Full textAbstract:
представлена классификации трёх разновидностей опухолей мозга: менингиома, глиома и опухоль гипофиза по магнитно-резонансная томографии (МРТ). В исследовании основным инструментом для классификации являются свёрточные нейронные сети. Приводятся постановка задачи, количество исходных изображений, разбиение входной выборки на обучаемую, тестовую и валидационную, нормализация входного набора данных и прочее. Приведено описание архитектуры свёрточной нейронной сети, которая используется для обучения модели классификации изображений опухоли мозга. В ней применяется заранее предобученная нейронная сеть EfficientNetB3, которая была обучена за счёт сервиса ImageNet, что является иерархически организованной базой данных изображений. Представлена архитектура свёрточной нейронной сети EfficientNetB3, где по цепочке продемонстрирована взаимосвязь между слоями. Рассматривается детализированный пример обучения приведённой свёрточной нейронной сети, где продемонстрировано, как происходит улучшение работы модели на тестовых и валидационных выборках в зависимости от количества эпох. Представлена сводная статистика при обучении, где выявлена эпоха с наилучшим результатом работы модели на валидационной выборке, что и является результатом обучения this paper provides an opportunity to classify three types of brain tumors: meningioma, glioma and pituitary tumor by magnetic resonance imaging (MRI). In the study, convolutional neural networks are the main tool for classification. The paper provides a statement of the problem, the number of source images, splitting the input sample into trainable, test and validation, normalization of the input data set, and so on. The paper also describes the architecture of a convolutional neural network, which is used to train a brain tumor image classification model. It uses a pre-trained neural network EfficientNetB3, which was trained at the expense of the ImageNet service, which is a hierarchically organized image database. This study also presents the architecture of the EfficientNetB3 convolutional neural network, where the relationship between the layers is demonstrated along the chain. A detailed example of training a reduced convolutional neural network is considered, which demonstrates how the model improves on test and validation sets depending on the number of epochs. The summary statistics during training is also presented, where the epoch with the best result of the model on the validation set was identified, which is the result of training
43
Rançon, Florian, Lionel Bombrun, Barna Keresztes, and Christian Germain. "Comparison of SIFT Encoded and Deep Learning Features for the Classification and Detection of Esca Disease in Bordeaux Vineyards." Remote Sensing 11, no. 1 (2018): 1. http://dx.doi.org/10.3390/rs11010001.
Full textAbstract:
Grapevine wood fungal diseases such as esca are among the biggest threats in vineyards nowadays. The lack of very efficient preventive (best results using commercial products report 20% efficiency) and curative means induces huge economic losses. The study presented in this paper is centered around the in-field detection of foliar esca symptoms during summer, exhibiting a typical “striped” pattern. Indeed, in-field disease detection has shown great potential for commercial applications and has been successfully used for other agricultural needs such as yield estimation. Differentiation with foliar symptoms caused by other diseases or abiotic stresses was also considered. Two vineyards from the Bordeaux region (France, Aquitaine) were chosen as the basis for the experiment. Pictures of diseased and healthy vine plants were acquired during summer 2017 and labeled at the leaf scale, resulting in a patch database of around 6000 images (224 × 224 pixels) divided into red cultivar and white cultivar samples. Then, we tackled the classification part of the problem comparing state-of-the-art SIFT encoding and pre-trained deep learning feature extractors for the classification of database patches. In the best case, 91% overall accuracy was obtained using deep features extracted from MobileNet network trained on ImageNet database, demonstrating the efficiency of simple transfer learning approaches without the need to design an ad-hoc specific feature extractor. The third part aimed at disease detection (using bounding boxes) within full plant images. For this purpose, we integrated the deep learning base network within a “one-step” detection network (RetinaNet), allowing us to perform detection queries in real time (approximately six frames per second on GPU). Recall/Precision (RP) and Average Precision (AP) metrics then allowed us to evaluate the performance of the network on a 91-image (plants) validation database. Overall, 90% precision for a 40% recall was obtained while best esca AP was about 70%. Good correlation between annotated and detected symptomatic surface per plant was also obtained, meaning slightly symptomatic plants can be efficiently separated from severely attacked plants.
44
Hemmer, Martin, Huynh Van Khang, Kjell Robbersmyr, Tor Waag, and Thomas Meyer. "Fault Classification of Axial and Radial Roller Bearings Using Transfer Learning through a Pretrained Convolutional Neural Network." Designs 2, no. 4 (2018): 56. http://dx.doi.org/10.3390/designs2040056.
Full textAbstract:
Detecting bearing faults is very important in preventing non-scheduled shutdowns, catastrophic failures, and production losses. Localized faults on bearings are normally detected based on characteristic frequencies associated with faults in time and frequency spectra. However, missing such characteristic frequency harmonics in a spectrum does not guarantee that a bearing is healthy, or noise might produce harmonics at characteristic frequencies in the healthy case. Further, some defects on roller bearings could not produce characteristic frequencies. To avoid misclassification, bearing defects can be detected via machine learning algorithms, namely convolutional neural network (CNN), support vector machine (SVM), and sparse autoencoder-based SVM (SAE-SVM). Within this framework, three fault classifiers based on CNN, SVM, and SAE-SVM utilizing transfer learning are proposed. Transfer of knowledge is achieved by extracting features from a CNN pretrained on data from the imageNet database to classify faults in roller bearings. The effectiveness of the proposed method is investigated based on vibration and acoustic emission signal datasets from roller bearings with artificial damage. Finally, the accuracy and robustness of the fault classifiers are evaluated at different amounts of noise and training data.
45
Hamdaoui, Halima El, Anass Benfares, Saïd Boujraf, et al. "High precision brain tumor classification model based on deep transfer learning and stacking concepts." Indonesian Journal of Electrical Engineering and Computer Science 24, no. 1 (2021): 167. http://dx.doi.org/10.11591/ijeecs.v24.i1.pp167-177.
Full textAbstract:
In this article, we proposed an intelligent clinical decision support system for the detection and classification of brain tumor from risk of malignancy index (RMI) images. To overcome the lack of labeled training data needed to train convolutional neural networks, we have used a deep transfer learning and stacking concepts. For this, we choosed seven convolutional neural networks (CNN) architectures already pre-trained on an ImageNet dataset that we precisely fit on magnetic resonance imaging (MRI) of brain tumors collected from the brain tumor segmentation (BraTS) 19 database. To improve the accuracy of our global model, we only predict as output the prediction that obtained the maximum score among the predictions of the seven pre-trained CNNs. We used a 10-way cross-validation approach to assess the performance of our main 2-class model: low-grade glioma (LGG) and high-grade glioma (HGG) brain tumors. A comparison of the results of our proposed model with those published in the literature, shows that our proposed model is more efficient than those published with an average test precision of 98.67%, an average f1 score of 98.62%, a test precision average of 98.06% and an average test sensitivity of 98.33%.
46
Khalil, Muhammad Ibrahim, Saif Ur Rehman, Mousa Alhajlah, et al. "Deep-COVID: Detection and Analysis of COVID-19 Outcomes Using Deep Learning." Electronics 11, no. 22 (2022): 3836. http://dx.doi.org/10.3390/electronics11223836.
Full textAbstract:
The coronavirus epidemic (COVID-19) is growing quickly around the globe. The first acute atypical respiratory illness was reported in December 2019, in Wuhan, China. This quickly spread from Wuhan city to other locations. Deep learning (DL) algorithms are one of the greatest solutions for consistently and readily recognizing COVID-19. Previously, many researchers used state-of-the-art approaches for the classification of COVID-19. In this paper, we present a deep learning approach with the EfficientnetB4 model, centered on transfer learning, for the classification of COVID-19. Transfer learning is a popular technique that uses pre-trained models that have been trained on the ImageNet database and employed on a new problem to increase generalization. We presented an in-depth training approach to extract the visual properties of COVID-19 in exchange for providing a medical assessment before infection testing. The proposed methodology is assessed on a publicly accessible X-ray imaging dataset. The proposed framework achieves an accuracy of 97%. Our model’s experimental findings demonstrate that it is extremely successful at identifying COVID-19 and that it may be supplied to health organizations as a precise, quick, and successful decision support system for COVID-19 identification.
47
Francis, Mercelin, Kalaiarasi Sonai Muthu Anbananthen, Deisy Chelliah, Subarmaniam Kannan, Sridevi Subbiah, and Jayakumar Krishnan. "Smart Farm-Care using a Deep Learning Model on Mobile Phones." Emerging Science Journal 7, no. 2 (2023): 480–97. http://dx.doi.org/10.28991/esj-2023-07-02-013.
Full textAbstract:
Deep learning and its models have provided exciting solutions in various image processing applications like image segmentation, classification, labeling, etc., which paved the way to apply these models in agriculture to identify diseases in agricultural plants. The most visible symptoms of the disease initially appear on the leaves. To identify diseases found in leaf images, an accurate classification system with less size and complexity is developed using smartphones. A labeled dataset consisting of 3171 apple leaf images belonging to 4 different classes of diseases, including the healthy ones, is used for classification. In this work, four variants of MobileNet models - pre-trained on the ImageNet database, are retrained to diagnose diseases. The model’s variants differ based on their depth and resolution multiplier. The results show that the proposed model with 0.5 depth and 224 resolution performs well - achieving an accuracy of 99.6%. Later, the K-means algorithm is used to extract additional features, which helps improve the accuracy to 99.7% and also measures the number of pixels forming diseased spots, which helps in severity prediction. Doi: 10.28991/ESJ-2023-07-02-013 Full Text: PDF
48
Et. al., B. Yamini Pushpa,. "Analysis On Radar Image Classification Using Deep Learning." Turkish Journal of Computer and Mathematics Education (TURCOMAT) 12, no. 11 (2021): 840–45. http://dx.doi.org/10.17762/turcomat.v12i11.5970.
Full textAbstract:
The progress of the last 10 years of deep learning technology has inspired many fields of research, such as the processing of radar signal, speech and audio recognition, etc. Data representation acquired with Lidar or camera sensors are used for most prominent deep learning models, leaving automotive radars seldom used. Despite their vital potential in adverse weather conditions and their ability to seamlessly measure the range of an object and radial speed. Since radar signals have still not been used, the available benchmarking data is lacking. In the recent past, however, the application of radar data to various profound learning algorithms has been very interesting, since more datasets are being provided. This article aims to describe a new method of grading applied for the synthetic aperture radar (SAR), followed by fine tuning in such a grading scheme; Pre-trained architectures in the ImageNet database were used; the VGG 16 had actually been used as a feature extractor and the new classifier was trained based on the extracted features. The Dataset used is the data acquisition and recognition (MSTAR) of the Moving and Stationary Traget; for ten (10) different classes we have achieved a final accuracy of 97.91 percent.
49
Hamdaoui, Halima El, Anass Benfares, Saïd Boujraf, et al. "High precision brain tumor classification model based on deep transfer learning and stacking concepts." Indonesian Journal of Electrical Engineering and Computer Science 24, no. 1 (2021): 167–77. https://doi.org/10.11591/ijeecs.v24.i1.pp167-177.
Full textAbstract:
In this article, we proposed an intelligent clinical decision support system for the detection and classification of brain tumor from risk of malignancy index (RMI) images. To overcome the lack of labeled training data needed to train convolutional neural networks, we have used a deep transfer learning and stacking concepts. For this, we choosed seven convolutional neural networks (CNN) architectures already pre-trained on an ImageNet dataset that we precisely fit on magnetic resonance imaging (MRI) of brain tumors collected from the brain tumor segmentation (BraTS) 19 database. To improve the accuracy of our global model, we only predict as output the prediction that obtained the maximum score among the predictions of the seven pre-trained CNNs. We used a 10-way cross-validation approach to assess the performance of our main 2-class model: low-grade glioma (LGG) and highgrade glioma (HGG) brain tumors. A comparison of the results of our proposed model with those published in the literature, shows that our proposed model is more efficient than those published with an average test precision of 98.67%, an average f1 score of 98.62%, a test precision average of 98.06% and an average test sensitivity of 98.33%.
50
Ayana, Gelan, Jinhyung Park, and Se-woon Choe. "Abstract 5052: Patchless deep transfer learning for improved mammographic breast mass classification." Cancer Research 82, no. 12_Supplement (2022): 5052. http://dx.doi.org/10.1158/1538-7445.am2022-5052.
Full textAbstract:
Abstract Purpose: Despite mammographic breast mass change being the most important finding in characterizing breast cancer in young women with dense breasts, a mammogram (Mg) is susceptible to false positives and false negatives in distinguishing between benign and malignant breast mass images. Additional tests such as ultrasound and biopsy might be needed to decide results. Setting aside the improvements in classifying breast mass Mg images via deep learning (DL), obtaining large training data and ensuring generalizations across different datasets with robust and well-optimized algorithms is a challenge. ImageNet based transfer learning has been utilized to address the unavailability of large datasets and robust algorithms. However, it is yet to achieve the desired accuracy, sensitivity, and specificity for DL models to be used as a standalone tool. Furthermore, previous works are computationally infeasible where exhaustive patch separation is carried out to segment the region of interest before training, which makes processing computationally complex and time-consuming. Here we propose a novel deep learning method based on multistage transfer learning from ImageNet and cancer cell line images pre-trained EfficientNetB2 model to classify mammographic breast mass as either benign or malignant. Methods: We trained our model on three publicly available datasets, 13,128 Digital Database for Screening Mammography (DDSM), 7632 INbreast, and 3816 Mammographic Image Analysis Society (MIAS) Mg breast mass images. Additionally, we trained our model on a mixed dataset of images from the three datasets to evaluate robustness. Data were sorted into 6:2:2 ratio for training, validation, and test, respectively. The microscopic cancer cell line dataset size was 38, 080 images. Results: We obtained an average 5-fold cross-validation AUC of 0.9999, test accuracy of 99.99%, sensitivity of 1, and specificity of 0.9998 on DDSM, AUC of 0.9997, test accuracy of 99.99%, sensitivity of 0.9972, and specificity of 0.9988 on INbreast, and AUC of 0.9987, test accuracy of 99.89%, sensitivity of 0.9987, specificity of 1 on MIAS, and AUC of 0.9997, test accuracy of 99.91%, sensitivity of 0.9993, and specificity of 0.9989 on the mixed dataset. Moreover, we acquired a P-value of 0.019 in the investigation of a statistically significant improvement in test accuracy from using our method compared to the conventional ImageNet based transfer learning on DDSM dataset. Conclusion: Our study suggests that utilizing cancer cell line images further improved the learning process alleviating the need for large Mg training data. Moreover, our method achieved better performance without applying the computationally complex patch separation task. The findings of this study are of crucial importance in the early diagnosis of breast cancer in young women with dense breasts where mammography struggles. Citation Format: Gelan Ayana, Jinhyung Park, Se-woon Choe. Patchless deep transfer learning for improved mammographic breast mass classification [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 5052.