To see the other types of publications on this topic, follow the link: Image retrieval deep learning.
Journal articles on the topic 'Image retrieval deep learning'
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 'Image retrieval deep learning.'
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
Maji, Subhadip, and Smarajit Bose. "CBIR Using Features Derived by Deep Learning." ACM/IMS Transactions on Data Science 2, no. 3 (2021): 1–24. http://dx.doi.org/10.1145/3470568.
Full textAbstract:
In a Content-based Image Retrieval (CBIR) System, the task is to retrieve similar images from a large database given a query image. The usual procedure is to extract some useful features from the query image and retrieve images that have a similar set of features. For this purpose, a suitable similarity measure is chosen, and images with high similarity scores are retrieved. Naturally, the choice of these features play a very important role in the success of this system, and high-level features are required to reduce the “semantic gap.” In this article, we propose to use features derived from pre-trained network models from a deep-learning convolution network trained for a large image classification problem. This approach appears to produce vastly superior results for a variety of databases, and it outperforms many contemporary CBIR systems. We analyse the retrieval time of the method and also propose a pre-clustering of the database based on the above-mentioned features, which yields comparable results in a much shorter time in most of the cases.
2
Chakraverti, Ashish. "Deep Learning based Smart Image Search Engine." International Journal for Research in Applied Science and Engineering Technology 12, no. 2 (2024): 1577–85. http://dx.doi.org/10.22214/ijraset.2024.58602.
Full textAbstract:
Abstract: This paper introduces a new reverse search engine integration into content-based image retrieval (CBIR) systems that employs convolutional neural networks (CNNs) for feature extraction. It generates global descriptors using pre-trained CNN architectures such as ResNet50, InceptionV3, and InceptionResNetV2. It retrieves visually similar images without depending on linguistic annotations. Comparative analysis against existing methods, such as Gabor Wavelet, CNN-SVM, Metaheuristic Algorithm, etc., has been tested, and it proves the superiority of the proposed algorithm, the Cartoon Texture Algorithm, in CBIR. As the Internet sees an exponential growth of different data types, the importance of CBIR continues to grow. In order to efficiently retrieve images, solely relying on image features while ignoring metadata is exactly what we need. As such, this paper is a reminder of the need for CBIR in this changing world. They showed that CBIR continues to be quite effective in the age of the Internet. Their proposed model for CBIR, which integrates ResNet-50-based feature extraction, a neural network model trained on different image datasets, and clustering techniques to make retrieval fast, provides a significant improvement in accuracy and efficiency for content-dependent image retrieval. This methodology is likely to be very useful as we work with the increasingly huge data of vision and beyond on the Internet. It provides a good basis for an effective image search and retrieval system
3
Deepika, Sivasankaran, Seena P. Sai, R. Rajesh, and Kanmani Madheswari. "Sketch Based Image Retrieval using Deep Learning Based Machine Learning." International Journal of Engineering and Advanced Technology (IJEAT) 10, no. 5 (2021): 79–86. https://doi.org/10.35940/ijeat.E2622.0610521.
Full textAbstract:
Sketch based image retrieval (SBIR) is a sub-domain of Content Based Image Retrieval(CBIR) where the user provides a drawing as an input to obtain i.e retrieve images relevant to the drawing given. The main challenge in SBIR is the subjectivity of the drawings drawn by the user as it entirely relies on the user's ability to express information in hand-drawn form. Since many of the SBIR models created aim at using singular input sketch and retrieving photos based on the given single sketch input, our project aims to enable detection and extraction of multiple sketches given together as a single input sketch image. The features are extracted from individual sketches obtained using deep learning architectures such as VGG16 , and classified to its type based on supervised machine learning using Support Vector Machines. Based on the class obtained, photos are retrieved from the database using an opencv library, CVLib , which finds the objects present in a photo image. From the number of components obtained in each photo, a ranking function is performed to rank the retrieved photos, which are then displayed to the user starting from the highest order of ranking up to the least. The system consisting of VGG16 and SVM provides 89% accuracy
4
Sivasankaran, Deepika, Sai Seena P, Rajesh R, and Madheswari Kanmani. "Sketch Based Image Retrieval using Deep Learning Based Machine Learning." International Journal of Engineering and Advanced Technology 10, no. 5 (2021): 79–86. http://dx.doi.org/10.35940/ijeat.e2622.0610521.
Full textAbstract:
Sketch based image retrieval (SBIR) is a sub-domain of Content Based Image Retrieval(CBIR) where the user provides a drawing as an input to obtain i.e retrieve images relevant to the drawing given. The main challenge in SBIR is the subjectivity of the drawings drawn by the user as it entirely relies on the user's ability to express information in hand-drawn form. Since many of the SBIR models created aim at using singular input sketch and retrieving photos based on the given single sketch input, our project aims to enable detection and extraction of multiple sketches given together as a single input sketch image. The features are extracted from individual sketches obtained using deep learning architectures such as VGG16 , and classified to its type based on supervised machine learning using Support Vector Machines. Based on the class obtained, photos are retrieved from the database using an opencv library, CVLib , which finds the objects present in a photo image. From the number of components obtained in each photo, a ranking function is performed to rank the retrieved photos, which are then displayed to the user starting from the highest order of ranking up to the least. The system consisting of VGG16 and SVM provides 89% accuracy
5
Li, Peng. "Image Color Recognition and Optimization Based on Deep Learning." Wireless Communications and Mobile Computing 2022 (August 9, 2022): 1–7. http://dx.doi.org/10.1155/2022/7226598.
Full textAbstract:
In order to solve the problem of image color recognition, this paper proposes a method of image color recognition and optimization based on deep learning and designs a postprocessing framework based on word bag model (bow). The framework uses CNN features and calculates feature similarity. The image sets with high similarity are input into the image classifier trained by bow clustering model as the preliminary retrieval results. The retrieval results are the categories with the largest number of images. The experimental results show that the image retrieval accuracy of the framework is 90.4% based on the same data set and classification category, which is 10% higher than the image retrieval algorithm based on CNN features. Conclusion. The color matching degree between the image color and the image to be retrieved has been greatly improved.
6
Kaur, Bhupinder. "A Deep Learning Approach for Content-Based Image Retrieval." INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 06 (2025): 1–9. https://doi.org/10.55041/ijsrem50977.
Full textAbstract:
Content-Based Image Retrieval (CBIR) aims to retrieve relevant images based on visual content rather than metadata, addressing the limitations of traditional retrieval methods. This study proposes a deep learning-based CBIR system utilizing Convolutional Neural Networks (CNNs) for automatic feature extraction. Leveraging the CIFAR-10 dataset, the system is evaluated against traditional handcrafted methods such as color histograms and color moments. Various retrieval paradigms image-based, text-based, sketch-based, and conceptual layout are analyzed for performance comparison. Experimental results demonstrate that CNN-based retrieval achieves over 85% accuracy, significantly outperforming traditional approaches. The system exhibits robustness to intra-class variation, occlusion, and background noise, establishing deep learning as a superior and scalable approach for large-scale CBIR applications. Keywords—Content-Based Image Retrieval, Deep Learning, CNN, Image Similarity, CIFAR-10, Feature Extraction, Image Retrieval Algorithms
7
Naveen, Mr Kommu. "A Review on Content Based Image Retrieval System Features derived by Deep Learning Models." International Journal for Research in Applied Science and Engineering Technology 9, no. 12 (2021): 42–57. http://dx.doi.org/10.22214/ijraset.2021.39172.
Full textAbstract:
Abstract: In a Content Based Image Retrieval (CBIR) System, the task is to retrieve similar images from a large database given a query image. The usual procedure is to extract some useful features from the query image, and retrieve images which have similar set of features. For this purpose, a suitable similarity measure is chosen, and images with high similarity scores are retrieved. Naturally the choice of these features play a very important role in the success of this system, and high level features are required to reduce the “semantic gap”. In this paper, we propose to use features derived from pre-trained network models from a deep- learning convolution network trained for a large image classification problem. This approach appears to produce vastly superior results for a variety of databases, and it outperforms many contemporary CBIR systems. We analyse the retrieval time of the method, and also propose a pre-clustering of the database based on the above-mentioned features which yields comparable results in a much shorter time in most of the cases. Keywords Content Based Image Retrieval Feature Selection Deep Learning Pre-trained Network Models Pre-clustering
8
Zena, Zena, Ahmed T. Sadiq, Omar Z. Akif, and El-Sayed M. El El-kenawy. "Enhancing Convolutional Neural Network for Image Retrieval." Journal of Intelligent Systems and Internet of Things 14, no. 2 (2025): 140–52. http://dx.doi.org/10.54216/jisiot.140212.
Full textAbstract:
With the continuous progress of image retrieval technology, the speed of searching for the required image from a large amount of image data has become an important issue. Convolutional neural networks (CNNs) have been used in image retrieval. However, many image retrieval systems based on CNNs have poor ability to express image features. Content-based Image Retrieval (CBIR) is a method of finding desired images from image databases. However, CBIR suffers from lower accuracy in retrieving images from large-scale image databases. In this paper, the proposed system is an improvement of the convolutional neural network for greater accuracy and a machine learning tool that can be used for automatic image retrieval. It includes two phases; the first phase (offline processing) consist of two stages; stage1 for CNN model classification while stage 2 for extracts high-level features directly from CNN by a flattening layer, which will be stored into a vector. In the second phase (online processing), the retrieval depends on query by image (QBI) from the system, which relies on the online CNN model stage to extract the features of the transmitted image. Afterward, an evaluation is conducted between the extracted features and the features that were previously stored by employing the Hamming distance to return all similar images. Last, it retrieves all the images and sends them to the system. Classification for images was achieved with 97.94% deep learning results, while for retrieved images, the deep learning was 98.94%. For this paper, work done on COREL image dataset. The images in the dataset used for training are more difficult than image classification due to the need for more computational resources. In the experimental part, training images using CNN achieved high accuracy, proving that the model has high accuracy in image retrieval.
9
Kumar, Suneel, Manoj Kumar Singh, and Manoj Kumar Mishra. "Improve Content-based Image Retrieval using Deep learning model." Journal of Physics: Conference Series 2327, no. 1 (2022): 012028. http://dx.doi.org/10.1088/1742-6596/2327/1/012028.
Full textAbstract:
Abstract The complexity of multimedia has expanded dramatically as a result of recent technology breakthroughs, and retrieval of similar multimedia material remains an ongoing research topic. Content-based image retrieval (CBIR) systems search huge databases for pictures that are related to the query image (QI). Existing CBIR algorithms extract just a subset of feature sets, limiting retrieval efficacy. The sorting of photos with a high degree of visual similarity is a necessary step in any image retrieval technique. Because a single feature is not resilient to image datasets modifications, feature combining, also known as feature fusion, is employed in CBIR to increase performance. This work describes a CBIR system in which combining DarkNet-19 and DarkNet-53 information to retrieve images. Experiments on the Wang (Corel 1K) database reveal a considerable improvement in precision over state-of-the-art classic techniques as well as Deep Convolutional Neural Network(DCNN).
10
Hadid, M. H., Z. T. Al-Qaysi, Qasim Mohammed Hussein, et al. "Semantic Image Retrieval Analysis Based on Deep Learning and Singular Value Decomposition." Applied Data Science and Analysis 2024 (March 25, 2024): 17–31. http://dx.doi.org/10.58496/adsa/2024/003.
Full textAbstract:
The exponential growth in the total quantity of digital images has necessitated the development of systems that are capable of retrieving these images. Content-based image retrieval is a technique used to get images from a database. The user provides a query image, and the system retrieves those photos from the database that are most similar to the query image. The image retrieval problem pertains to the task of locating digital photographs inside extensive datasets. Image retrieval researchers are transitioning from the use of keywords to the utilization of low-level characteristics and semantic features. The push for semantic features arises from the issue of subjective and time-consuming keywords, as well as the limitation of low-level characteristics in capturing high-level concepts that users have in mind. The main goal of this study is to examine how convolutional neural networks can be used to acquire advanced visual features. These high-level feature descriptors have the potential to be the most effective compared to the handcrafted feature descriptors in terms of image representation, which would result in improved image retrieval performance. The (CBIR-VGGSVD) model is an ideal solution for content-based image retrieval that is based on the VGG-16 algorithm and uses the Singular Value Decomposition (SVD) technique. The suggested model incorporates the VGG-16 model for the purpose of extracting features from both the query images and the images kept in the database. Afterwards, the dimensionality of the features retrieved from the VGG-16 model is reduced using SVD. Then, we compare the query photographs to the dataset images using the cosine metric to see how similar they are. When all is said and done, images that share a high degree of similarity will be successfully extracted from the dataset. A validation of the retrieval performance of the CBIR-VGGSVD model is performed using the Corel-1K dataset. When the VGG-16 standard model is the sole one used, the implementation will produce an average precision of 0.864. On the other hand, when the CBIR-VGGSVD model is utilized, this average precision is revealed to be (0.948). The findings of the retrieval ensured that the CBIR-VGGSVD model provided an improvement in performance on the test pictures that were utilized, surpassing the performance of the most recent approaches.
11
Wang, Ziyang, Wei Zheng, and Youguang Chen. "Deep learning for fast bronze inscription image retrieval." Journal of Chinese Writing Systems 4, no. 4 (2020): 291–96. http://dx.doi.org/10.1177/2513850220964956.
Full textAbstract:
Collections of bronze inscription images are increasing rapidly. To use these images efficiently, we proposed an effective content-based image retrieval framework using deep learning. Specifically, we extract discriminative local features for image retrieval using the activations of the convolutional neural network and binarize the extracted features for improving the efficiency of image retrieval, firstly. Then, we use the cosine metric and Euclidean metric to calculate the similarity between the query image and dataset images. The result shows that the proposed framework has an impressive accuracy.
12
Anish, L., and S. Thiyagarajan. "Unveiling Visual Treasures: Harnessing Deep Learning for Content-Based Image Retrieval." Indian Journal Of Science And Technology 17, no. 25 (2024): 2610–21. http://dx.doi.org/10.17485/ijst/v17i25.745.
Full textAbstract:
Objective: An essential aspect of computer vision is content-based image retrieval (CBIR), which enables users to search for images based on their visual content instead of created annotations. Advances in technology have resulted in a significant rise in the complexity of multimedia content and the emergence of new research fields centered on similar multimedia material retrieval. The efficacy of retrieval is impacted by the limits of the present CBIR systems, which result from overlooked algorithms and computing restrictions. Methods: This research introduces a novel approach employing the Siamese Edge Attention Layered Convonet (SEAL Convonet) for Image Retrieval. We utilize the CBIR image dataset through Gaussian smoothing to enhance image quality for data preprocessing and the Canny Edge Detector (CED) for edge detection, following pre-processing. The Histogram of Oriented Gradients (HOG) is used for feature extraction to extract complex textures and patterns from the images. Findings: This approach is implemented and tested through simulations as well as the results indicate a substantial positive deviation in the performance and retrieval of the images compared to existing methods. The performance metrics are accuracy (97 %), precision (94 %), recall (91 %), F1-Score (97 %), False Positive Rate (FNR) (0.0013), Matthew's correlation coefficient (MCC) (0.85), and False Negative Rate (FPR) (0.0036) show the measurements of this proposed model. Application: The state of the art in this work is researching the influence of optimizers on the accuracy process, as indicated by the findings. Keywords: CBIR, Gaussian smoothing, Canny Edge Detector, Histogram of oriented gradients (HOG), Siamese Edge Attention Layered convonet (SEAL Convonet), Database
13
Abdulla P., Shaik, and Abdul Razak T. "Retrieval-Based Inception V3-Net Algorithm and Invariant Data Classification using Enhanced Deep Belief Networks for Content-Based Image Retrieval." Scientific Temper 15, spl-1 (2025): 415–24. https://doi.org/10.58414/scientifictemper.2024.15.spl.48.
Full textAbstract:
In the present scenario, Content-Based Image Retrieval (CBIR) performs a constantly changing function that makes use gain knowledge from images. Moreover, it is also the dynamic sector of research and was recently rewarded due to the drastic increase in the performance of digital images. To retrieve images from the massive dataset, experts utilize Content Based Image Retrieval. This approach automatically indexes and retrieves images depending upon the contents of the image, and the developing techniques for mining images are based on the CBIR systems. Based on the visual characteristics of the input image, object pattern, texture, color, shape, layout, and position classifications are applied, and indexing is carried out. When issues arise during feature extraction, deep learning approaches help to resolve them. A method called RIV3-NET, which stands for Retrieval-Based Inception V3, was used to classify the features. Classifying image invariant data using Enhanced Deep Belief Networks (EDBN) is necessary to decrease noise and improve displacement with smoothness. The simulation outcomes demonstrate the improved picture retrieval and parametric analysis.
14
Jin Hang Zhang. "Exploring Deep Learning Approach on Semantic Gap: A Comprehensive Review." Journal of Information Systems Engineering and Management 10, no. 38s (2025): 1075–94. https://doi.org/10.52783/jisem.v10i38s.7065.
Full textAbstract:
With the prevalence of the Internet and smartphones, users upload a large number of images to the web. However, it is challenging for users to find what they really need from the vast sea of images. It is also difficult for Internet companies to effectively integrate their massive image data resources. In traditional content-based image retrieval, images are indexed by their low-level visual features, which leads to a key problem: the semantic gap between low-level features and high-level semantic concepts. To address this issue, semantic-based image retrieval has been proposed as a solution to bridge the semantic gap, making it a key technical challenge in the field of image retrieval. To tackle these challenges, this proposal presents a novel multi-annotation method for images and develops an image retrieval system based on deep learning and image semantic content. Preparatory work, including a literature review and methodology development, will be conducted to implement the semantic-based image retrieval system and efficiently utilize the vast number of available images.
15
V, Vinitha, and Velantina V. "Content Based Image Retrieval from Auto Encoders Using Keras and Tensor Flow Python API a Deep Learning Technique." Volume 5 - 2020, Issue 9 - September 5, no. 9 (2020): 869–71. http://dx.doi.org/10.38124/ijisrt20sep116.
Full textAbstract:
As the technology is evolving new methods and techniques are determined and implemented in a smart way to improve and achieve a greater insight in this smart era. The retrieval of image is popularly growing in this emerging trend. In this paper we have used how to build a very simple image retrieval system using a special type of Neural Network called auto encoders. Here the images can be retrieved with visual contents textures, shape and this method of image retrieval is called content based image retrieval.
16
Reddy, Tatireddy Subba, Sanjeevaiah K., Sajja Karthik, Mahesh Kumar, and Vivek D. "Content-Based Image Retrieval Using Hybrid Densenet121-Bilstm and Harris Hawks Optimization Algorithm." International Journal of Software Innovation 11, no. 1 (2023): 1–15. http://dx.doi.org/10.4018/ijsi.315661.
Full textAbstract:
In the field of digital data management, content-based image retrieval (CBIR) has become one of the most important research areas, and it is used in many fields. This system searches a database of images to retrieve most visually comparable photos to a query image. It is based on features derived directly from the image data, rather than on keywords or annotations. Currently, deep learning approaches have demonstrated a strong interest in picture recognition, particularly in extracting information about the features of the image. Therefore, a Densenet-121 is employed in this work to extract high-level and deep characteristics from the images. Afterwards, the training images are retrieved from the dataset and compared to the query image using a Bidirectional LSTM (BiLSTM) classifier to obtain the relevant images. The investigations are conducted using a publicly available dataset named Corel, and the f-measure, recall, and precision metrics are used for performance assessment. Investigation outcomes show that the proposed technique outperforms the existing image retrieval techniques.
17
Junwei Xin, Junwei Xin, Famao Ye Junwei Xin, Yuanping Xia Famao Ye, Yan Luo Yuanping Xia, and Xiaoyong Chen Yan Luo. "A New Remote Sensing Image Retrieval Method Based on CNN and YOLO." 網際網路技術學刊 24, no. 2 (2023): 233–42. http://dx.doi.org/10.53106/160792642023032402002.
Full textAbstract:
<>Retrieving remote sensing images plays a key role in RS fields, which activates researchers to design a highly effective extraction method of image high-level features. However, despite the advanced features of the image can be extracted by deep-learning method, features fail to cover the overall information due to its rich and complex background. Extract key regions from RS images, recede background interference and retrieval accuracy needs to be solved. Combined YOLOv5 target recognition algorithm with deep-learning method, this paper proposes a novel retrieval method based on target critical region detection. Firstly, the key retrieval regions have been identified. YOLOv5 target recognition algorithm has been used to identify the key regions of the image and served as the retrieval regions. Secondly, the retrieval characteristics are determined. Combining with the CNN model ResNet50, the retrieval features are extracted from the retrieval regions acquired in the previous step, in addition, PCA method has been used to reduce the dimension of the retrieval features. Finally, using weighted distance based on class probability to measure the similarity between a query and retrieve images. Experimental results show that the proposed method can extract better image retrieval features and improve the retrieval performance of RS image.<>
18
Gao, Yuru. "Image Retrieval based on Deep Learning." Frontiers in Computing and Intelligent Systems 5, no. 3 (2023): 154–56. http://dx.doi.org/10.54097/fcis.v5i3.14054.
Full textAbstract:
With the rapid growth of image data, how to efficiently and accurately extract useful features from massive image data and perform fast image retrieval has become an important research direction. This study focuses on the design and training of deep learning-based image feature extraction networks to improve the robustness and generalization of image features by optimizing the network structure and loss function. In order to evaluate the performance of the system, this study also designs appropriate evaluation indicators and conducts corresponding experiments. Through experimental verification, the results show that these methods can effectively improve the performance of image feature extraction and image retrieval, and have broad potential in practical applications.
19
Luo, Qing, Xiang Gao, Bo Jiang, Xueting Yan, Wanyuan Liu, and Junchao Ge. "A review of fine-grained sketch image retrieval based on deep learning." Mathematical Biosciences and Engineering 20, no. 12 (2023): 21186–210. http://dx.doi.org/10.3934/mbe.2023937.
Full textAbstract:
<abstract> <p>Sketch image retrieval is an important branch of the image retrieval field, mainly relying on sketch images as queries for content search. The acquisition process of sketch images is relatively simple and in some scenarios, such as when it is impossible to obtain photos of real objects, it demonstrates its unique practical application value, attracting the attention of many researchers. Furthermore, traditional generalized sketch image retrieval has its limitations when it comes to practical applications; merely retrieving images from the same category may not adequately identify the specific target that the user desires. Consequently, fine-grained sketch image retrieval merits further exploration and study. This approach offers the potential for more precise and targeted image retrieval, making it a valuable area of investigation compared to traditional sketch image retrieval. Therefore, we comprehensively review the fine-grained sketch image retrieval technology based on deep learning and its applications and conduct an in-depth analysis and summary of research literature in recent years. We also provide a detailed introduction to three fine-grained sketch image retrieval datasets: Queen Mary University of London (QMUL) ShoeV2, ChairV2 and PKU Sketch Re-ID, and list common evaluation metrics in the sketch image retrieval field, while showcasing the best performance achieved for these datasets. Finally, we discuss the existing challenges, unresolved issues and potential research directions in this field, aiming to provide guidance and inspiration for future research.</p> </abstract>
20
Tang, Xu, Xiangrong Zhang, Fang Liu, and Licheng Jiao. "Unsupervised Deep Feature Learning for Remote Sensing Image Retrieval." Remote Sensing 10, no. 8 (2018): 1243. http://dx.doi.org/10.3390/rs10081243.
Full textAbstract:
Due to the specific characteristics and complicated contents of remote sensing (RS) images, remote sensing image retrieval (RSIR) is always an open and tough research topic in the RS community. There are two basic blocks in RSIR, including feature learning and similarity matching. In this paper, we focus on developing an effective feature learning method for RSIR. With the help of the deep learning technique, the proposed feature learning method is designed under the bag-of-words (BOW) paradigm. Thus, we name the obtained feature deep BOW (DBOW). The learning process consists of two parts, including image descriptor learning and feature construction. First, to explore the complex contents within the RS image, we extract the image descriptor in the image patch level rather than the whole image. In addition, instead of using the handcrafted feature to describe the patches, we propose the deep convolutional auto-encoder (DCAE) model to deeply learn the discriminative descriptor for the RS image. Second, the k-means algorithm is selected to generate the codebook using the obtained deep descriptors. Then, the final histogrammic DBOW features are acquired by counting the frequency of the single code word. When we get the DBOW features from the RS images, the similarities between RS images are measured using L1-norm distance. Then, the retrieval results can be acquired according to the similarity order. The encouraging experimental results counted on four public RS image archives demonstrate that our DBOW feature is effective for the RSIR task. Compared with the existing RS image features, our DBOW can achieve improved behavior on RSIR.
21
Syed Qamrul Kazmi, Et al. "Image Retrieval Using Auto Encoding Features In Deep Learning." International Journal on Recent and Innovation Trends in Computing and Communication 11, no. 10 (2023): 155–71. http://dx.doi.org/10.17762/ijritcc.v11i10.8478.
Full textAbstract:
The latest technologies and growth in availability of image storage in day to day life has made a vast storage place for the images in the database. Several devices which help in capturing the image contribute to a huge repository of images. Keeping in mind the daily input in the database, one must think of retrieving those images according to certain criteria mentioned. Several techniques such as shape of the object, Discrete Wavelet transform (DWT), texture features etc. were used in determining the type of image and classifying them. Segmentation also plays a vital role in image retrieval but the robustness is lacking in most of the cases. The process of retrieval mainly depends on the special characteristics possessed by an image rather than the whole image. Two types of image retrieval can be seen. One with a general object and the other which may be specific to some type of application. Modern deep neural networks for unsupervised feature learning like Deep Autoencoder (AE) learn embedded representations by stacking layers on top of each other. These learnt embedded-representations, however, may degrade as the AE network deepens due to vanishing gradient, resulting in decreased performance. We have introduced here the ResNet Autoencoder (RAE) and its convolutional version (C-RAE) for unsupervised feature based learning. The proposed model is tested on three distinct databases Corel1K, Cifar-10, Cifar-100 which differ in size. The presented algorithm have significantly reduced computation time and provided very high image retrieval levels of accuracy.
22
Kiran, Aqsa, Shahzad Ahmad Qureshi, Asifullah Khan, et al. "Reverse Image Search Using Deep Unsupervised Generative Learning and Deep Convolutional Neural Network." Applied Sciences 12, no. 10 (2022): 4943. http://dx.doi.org/10.3390/app12104943.
Full textAbstract:
Reverse image search has been a vital and emerging research area of information retrieval. One of the primary research foci of information retrieval is to increase the space and computational efficiency by converting a large image database into an efficiently computed feature database. This paper proposes a novel deep learning-based methodology, which captures channel-wise, low-level details of each image. In the first phase, sparse auto-encoder (SAE), a deep generative model, is applied to RGB channels of each image for unsupervised representational learning. In the second phase, transfer learning is utilized by using VGG-16, a variant of deep convolutional neural network (CNN). The output of SAE combined with the original RGB channel is forwarded to VGG-16, thereby producing a more effective feature database by the ensemble/collaboration of two effective models. The proposed method provides an information rich feature space that is a reduced dimensionality representation of the image database. Experiments are performed on a hybrid dataset that is developed by combining three standard publicly available datasets. The proposed approach has a retrieval accuracy (precision) of 98.46%, without using the metadata of images, by using a cosine similarity measure between the query image and the image database. Additionally, to further validate the proposed methodology’s effectiveness, image quality has been degraded by adding 5% noise (Speckle, Gaussian, and Salt pepper noise types) in the hybrid dataset. Retrieval accuracy has generally been found to be 97% for different variants of noise
23
Garad, Nakshatra. "Smart Video Surveillance Using Deep Learning." International Journal for Research in Applied Science and Engineering Technology 12, no. 4 (2024): 5392–96. http://dx.doi.org/10.22214/ijraset.2024.60441.
Full textAbstract:
Abstract: There is a lot of assessment happening in the business about video observation among them; the occupation of CCTV accounts has been blocked. CCTV cameras are put all around the spots for perception and security. In today's digital age, the increasing availability of data and advancements in computer vision have paved the way for numerous applications of object detection. This powerful technology has found its significance in various domains, including video surveillance and image retrieval systems. Object detection enables machines to identify and locate objects within images or video frames, providing valuable insights and aiding in decision-making processes. This article explores the applications, challenges, techniques, and future trends of object detection in the context of video surveillance and image retrieval systems. Object detection is a computer vision technique that involves identifying and localizing objects within images or video frames. Unlike image classification, which assigns a single label to an entire image, object detection goes a step further by detecting and delineating the individual objects present. It enables computers to comprehend visual data and interact with the world, much like humans do
24
Gagandeep Kaur, Vedant Pinjarkar, Rutuja Rajendra, Latika Pinjarkar, Jaspal Bagga, Poorva Agrawal,. "Deep Learning Model for Retrieving Color Logo Images in Content Based Image Retrieval." Journal of Electrical Systems 20, no. 2s (2024): 1325–33. http://dx.doi.org/10.52783/jes.1773.
Full textAbstract:
Content-Based Image retrieval (CBIR) has gained a magnificent deal of consideration because of the digital image data's epidemic growth. The advancement of deep learning has enabled Convolutional Neural Networks to become an influential technique for extraction of discriminative image features. In recent years, convolutional neural networks (CNNs) have proven extremely effective at extracting unique information from images. In contrast to text-based image retrieval, CBIR gathers comparable images based primarily on their visual content. The use of deep learning, especially CNNs, for feature extraction and image processing has been shown to perform better than other techniques. In the proposed study, we investigate CNNs for CBIR focusing on how well they extract discriminative visual features and facilitate accurate image retrieval. Also Principal Component Analysis and Linear Discriminant Analysis are combined for optimization of features resulting in boosting the retrieval results. Using hierarchical representations learned by CNNs, we aim to improve retrieval accuracy and efficiency. In comparison with conventional retrieval techniques, our proposed CBIR system shows superior performance on a benchmark dataset.
25
Ravi, G. "Content-Based Image Retrieval Using Deep Feature Extraction with ResNet-50." INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 05 (2025): 1–9. https://doi.org/10.55041/ijsrem48676.
Full textAbstract:
Abstract: This project presents a Content-Based Image Retrieval (CBIR) system that utilizes deep learning to improve the efficiency and accuracy of image similarity search. The system leverages a pre-trained ResNet-50 convolutional neural network, repurposed as a deep feature extractor by removing its final classification layers. Input images are first pre- processed and then passed through the network to extract high-dimensional feature vec- tors that capture rich visual semantics. These deep features are compared using cosine similarity to identify visually similar images. The system supports real-time image up- loads and retrieval by matching queries against a pre computed dataset of image fea- tures, enabling fast and responsive search capabilities. By replacing traditional hand- crafted features with deep feature representations, the system achieves significantly higher retrieval accuracy and robustness across various image types and domains. This approach demonstrates strong potential for practical deployment in areas such as digital asset management, visual search engines, and e-commerce product discovery, where visual similarity plays a critical role. Overall, the integration of deep learning into CBIR systems represents a significant advancement in the field of image search and retrieval. Keywords: CBIR, Deep Learning, ResNet-50, Feature Extraction, Image Simi- larity
26
Sikandar, Shahbaz, Rabbia Mahum, and AbdulMalik Alsalman. "A Novel Hybrid Approach for a Content-Based Image Retrieval Using Feature Fusion." Applied Sciences 13, no. 7 (2023): 4581. http://dx.doi.org/10.3390/app13074581.
Full textAbstract:
The multimedia content generated by devices and image processing techniques requires high computation costs to retrieve images similar to the user’s query from the database. An annotation-based traditional system of image retrieval is not coherent because pixel-wise matching of images brings significant variations in terms of pattern, storage, and angle. The Content-Based Image Retrieval (CBIR) method is more commonly used in these cases. CBIR efficiently quantifies the likeness between the database images and the query image. CBIR collects images identical to the query image from a huge database and extracts more useful features from the image provided as a query image. Then, it relates and matches these features with the database images’ features and retakes them with similar features. In this study, we introduce a novel hybrid deep learning and machine learning-based CBIR system that uses a transfer learning technique and is implemented using two pre-trained deep learning models, ResNet50 and VGG16, and one machine learning model, KNN. We use the transfer learning technique to obtain the features from the images by using these two deep learning (DL) models. The image similarity is calculated using the machine learning (ML) model KNN and Euclidean distance. We build a web interface to show the result of similar images, and the Precision is used as the performance measure of the model that achieved 100%. Our proposed system outperforms other CBIR systems and can be used in many applications that need CBIR, such as digital libraries, historical research, fingerprint identification, and crime prevention.
27
S. Sayed, Mahmoud, Ahmed A. A. Gad-Elrab, Khaled A. Fathy, and Kamal R. Raslan. "A deep learning content-based image retrieval approach using cloud computing." Indonesian Journal of Electrical Engineering and Computer Science 29, no. 3 (2023): 1577. http://dx.doi.org/10.11591/ijeecs.v29.i3.pp1577-1589.
Full textAbstract:
Due to the rapid growth in multimedia content and its visual complexity, contentbased image retrieval (CBIR) has become a very challenging task. Existing works achieve high precision values at first retrieval levels such as top 10 and top 20 images, but low precision values at subsequent levels such as top 40, 50, and 70, so the goal of this paper is to propose a new CBIR approach that achieves high precision values at all retrieval levels. The proposed method combines features extracted from the pre-trained AlexNet model and discrete cosine transform (DCT). Then principal components analysis (PCA) is performed on AlexNet’s features and feeding these combination to multiclass support vector machine (SVM). The euclidean distance is used to measure the similarity between query and stored images features within the predicted class by SVM. Finally top similar images are ranked and retrieved. All above techniques require huge computational power which may not be available on client machine thus, the processing of these tasks is processed on cloud. Experimental results on the benchmark Corel-1k show that the proposed method achieves high precision value 97% along all retrieval levels top 10, 20 and 70 images and requiring less memory compared to other methods.
28
Mahmoud, S. Sayed, A. A. Gad-Elrab Ahmed, A. Fathy Khaled, and R. Raslan Kamal. "A deep learning content-based image retrieval approach using cloud computing." A deep learning content-based image retrieval approach using cloud computing 29, no. 3 (2023): 1577–89. https://doi.org/10.11591/ijeecs.v29.i3.pp1577-1589.
Full textAbstract:
Due to the rapid growth in multimedia content and its visual complexity, contentbased image retrieval (CBIR) has become a very challenging task. Existing works achieve high precision values at first retrieval levels such as top 10 and top 20 images, but low precision values at subsequent levels such as top 40, 50, and 70, so the goal of this paper is to propose a new CBIR approach that achieves high precision values at all retrieval levels. The proposed method combines features extracted from the pre-trained AlexNet model and discrete cosine transform (DCT). Then principal components analysis (PCA) is performed on AlexNet’s features and feeding these combination to multiclass support vector machine (SVM). The euclidean distance is used to measure the similarity between query and stored images features within the predicted class by SVM. Finally top similar images are ranked and retrieved. All above techniques require huge computational power which may not be available on client machine thus, the processing of these tasks is processed on cloud. Experimental results on the benchmark Corel-1k show that the proposed method achieves high precision value 97% along all retrieval levels top 10, 20, and 70 images and requiring less memory compared to other methods.
29
Liu, Yangyang, Minghua Tian, Chang Xu, and Lixiang Zhao. "Neural network feature learning based on image self-encoding." International Journal of Advanced Robotic Systems 17, no. 2 (2020): 172988142092165. http://dx.doi.org/10.1177/1729881420921653.
Full textAbstract:
With the rapid development of information technology and the arrival of the era of big data, people’s access to information is increasingly relying on information such as images. Today, image data are showing an increasing trend in the form of an index. How to use deep learning models to extract valuable information from massive data is very important. In the face of such a situation, people cannot accurately and timely find out the information they need. Therefore, the research on image retrieval technology is very important. Image retrieval is an important technology in the field of computer vision image processing. It realizes fast and accurate query of similar images in image database. The excellent feature representation not only can represent the category information of the image but also capture the relevant semantic information of the image. If the neural network feature learning expression is combined with the image retrieval field, it will definitely improve the application of image retrieval technology. To solve the above problems, this article studies the problems encountered in deep learning neural network feature learning based on image self-encoding and discusses its feature expression in the field of image retrieval. By adding the spatial relationship information obtained by image self-encoding in the neural network training process, the feature expression ability of the selected neural network is improved, and the neural network feature learning based on image coding is successfully applied to the popular field of image retrieval.
30
Hassan Khan, Muzamil Mehboob, Amjad Ali, Lubna Rani, Dr. Khawaja Tehseen Ahmed, and Raza Iqbal. "Deep Learning using Spatial Distances, Normalized Coordinates, Scaling and Visual Words for Large Datasets." STATISTICS, COMPUTING AND INTERDISCIPLINARY RESEARCH 6, no. 2 (2024): 133–67. http://dx.doi.org/10.52700/scir.v6i2.163.
Full textAbstract:
Image Retrieval has become popular and crucial task and the number of digital images on (web servers) amplified, it became increasingly very difficult to classify and track images. Many methods have been used to make image exploration effective and reliable, such as search based on the file name, image tagging, etc. but none have proved a good idea to work in real scenario. Our proposed methodology applies deep learning using spatial distances, normalized coordinates, scaling and visual words for large data sets for retrieval of images with highest accuracy. The proposed methodology has three basic steps: the first is Content Analysis. The image is passed through coarser intervolving phase, second is CNN, third is RGB color evaluation, fourth is Retrieved feature vectors and fifth is results derivation. Proposed methodology was applied on the three famous datasets namely, Cifar-100, FTVL and Fashion. Experiments conducted on these datasets have shown outstanding results.
31
Ovais, Rashid Khan, and Iqbal Bhat Javaid. "Delving into the Depths of Image Retrieval Systems in the Light of Deep Learning: A Review." Indian Journal of Science and Technology 16, no. 34 (2023): 2693–702. https://doi.org/10.17485/IJST/v16i34.1341.
Full textAbstract:
Abstract <strong>Objective:</strong> The objective of this study is to conduct a comprehensive review of existing research and literature in the field of Content-Based Image Retrieval (CBIR). This review highlights the key challenges associated with the extraction and representation of visual semantics of images. This paper discusses the measure used computing similarity and ranking of retrieved images by CBIR system. The review discusses limitation of traditional approaches and also highlights the challenges with the current deep learning methods in semantic feature representation, defining the similarity metrics and indexing. This paper also highlights scalability and generalization challenges in implementing real environment. <strong>Methods:</strong> A thorough literature review was conducted on wellestablished databases, including Scopus, Web of Science, IEEE Xplore, ACM, and Science Direct, employing appropriate keywords. Mention the period of coverage. Pertinent search terms encompassed local feature representation, global feature representation, low-level features, high level features, semantic gap, image embeddings, handcrafted features, deep learning, image descriptors, similarity, and image indexing, with the aim of exploring content-based image retrieval systems. Comparative analysis was performed on the chosen articles, taking into account factors such as algorithms, methodologies, datasets, and evaluation metrics. The results discussed using comparative analysis, ensuring a comprehensive overview of recent literature on content-based image retrieval, offering valuable insights and highlighting emerging trends in the field. <strong>Findings :</strong> The research uncovers the novelty in the realm of contentbased image retrieval (CBIR) by highlighting the challenge of high-level visual semantics when comparing images, as perceived by humans. It emphasizes that feature extraction methods and choices significantly influence CBIR system performance, stressing the importance of selecting suitable features and similarity measures based on image dataset characteristics and application requirements. The study underscores the persistent obstacle of the semantic gap between low-level visual features and high-level semantic concepts, encouraging exploration of diverse approaches like deep learning, relevance feedback, and ontology-based methods to bridge this gap. Particularly, deep learn-ing techniques, notably Convolutional Neural Networks (CNNs), have shown promising results in CBIR by automatically learning hierarchical representations capturing high-level semantic information. However, the review also highlights the challenges of scaling deep learning methods and the limited accessibility of precisely labelled datasets, which can hinder performance and generalization across diverse image datasets and real-world scenarios. Deep learning models pose interpretability challenges due to their complex, opaque nature and hierarchical semantic representations. <strong>Keywords:</strong> CBIR; ContentBased Image Retrieval; Deep Learning; Convolutional Neural Network; Local Features; Global Features; Similarity Metric; Semantic Gap
32
Tseng, Chien-Hao, Chia-Chien Hsieh, Dah-Jing Jwo, Jyh-Horng Wu, Ruey-Kai Sheu, and Lun-Chi Chen. "Person Retrieval in Video Surveillance Using Deep Learning–Based Instance Segmentation." Journal of Sensors 2021 (August 21, 2021): 1–12. http://dx.doi.org/10.1155/2021/9566628.
Full textAbstract:
Video surveillance systems are deployed at many places such as airports, train stations, and malls for security and monitoring purposes. However, it is laborious to search for and retrieve persons in multicamera surveillance systems, especially with cluttered backgrounds and appearance variations among multiple cameras. To solve these problems, this paper proposes a person retrieval method that extracts the attributes of a masked image using an instance segmentation module for each object of interest. It uses attributes such as color and type of clothes to describe a person. The proposed person retrieval system involves four steps: (1) using the YOLACT++ model to perform pixelwise person segmentation, (2) conducting appearance-based attribute feature extraction using a multiple convolutional neural network classifier, (3) employing a search engine with a fundamental attribute matching approach, and (4) implementing a video summarization technique to produce a temporal abstraction of retrieved objects. Experimental results show that the proposed retrieval system can achieve effective retrieval performance and provide a quick overview of retrieved content for multicamera surveillance systems.
33
Bhaskar, Dr T., Dr Y. Ramadevi, Dr Pasam Naga Kavitha, and Padala Sravan. "MCBIR: Deep Learning based Framework for Efficient Content Based Image Retrieval System of Medical Images." International Journal of Electrical and Electronics Research 12, no. 4 (2024): 1364–73. https://doi.org/10.37391/ijeer.120430.
Full textAbstract:
Content-Based Image Retrieval (CBIR) in computer vision applications, enables retrieval of images reflecting user intent. Traditionally CBIR is based on image processing techniques. With the emergence of Artificial Intelligence (AI), it is now possible to realize CBIR using learning-based approaches. Particularly deep learning techniques such as Convolutional Neural Network (CNN) are efficient for image analysis. In this paper, we proposed a framework known Medical Content Based Image Retrieval System (MCBIRS), which exploits pre-trained CNN variants for retrieving medical images based on image input. The framework has an offline phase for extracting visual features from training data and an online phase for processing given user queries. The descriptors obtained by CNN variants in the offline phase are persisted in a database. These are later used in the online phase to compute the distance between persisted descriptors and input image descriptor. A set of closely matching images are returned against the query image based on similarity. We proposed an algorithm known as Learning-based Medical Image Retrieval (LbMIR) to realize MCBIRS. We also implemented a re-ranking of results retrieved by the framework using other techniques. The performance of LbMIR is evaluated and compared with the state-of-the-art methods such as Bag of Visual Words (BoVW) and Histogram of Oriented Gradients (HOG). Empirical results using medical image dataset revealed that CNN variants outperformed BoVW and HOG methods. On test data, the highest performance is achieved by the proposed system with 90% mean top-k precision, demonstrating its practical implications. On the training data highest performance is achieved by proposed system (CNN variants) re-ranked with HOG with 92.30% mean top-k precision.
34
Thanh, Van The, Do Quang Khoi, Le Huu Ha, and Le Manh Thanh. "SIR-DL: AN ARCHITECTURE OF SEMANTIC-BASED IMAGE RETRIEVAL USING DEEP LEARNING TECHNIQUE AND RDF TRIPLE LANGUAGE." Journal of Computer Science and Cybernetics 35, no. 1 (2019): 39–56. http://dx.doi.org/10.15625/1813-9663/35/1/13097.
Full textAbstract:
The problem of finding and identifying semantics of images is applied in multimedia applications of many different fields such as Hospital Information System, Geographic Information System, Digital Library System, etc. In this paper, we propose the semantic-based image retrieval (SBIR) system based on the deep learning technique; this system is called as SIR-DL that generates visual semantics based on classifying image contents. At the same time we identify the semantics of similar images on Ontology, which describes semantics of visual features of images. Firstly, the color and spatial features of segmented images are we extracted and these visual feature vectors are trained on the deep neural network to obtain visual words vectors. The process of image retrieval is executed rely on semantic classification of SIR-DL according to the visual feature vector of the query image from which it produces a visual word vector. Then, we retrieve it on Ontology to provide the identities and the semantics of similar images corresponds to a similarity measure. In order to carry out SIR-DL, the algorithms and diagram of this image retrieval system are proposed after that we implement them on ImageCLEF@IAPR, which has 20,000 images. On the base of the experimental results, the effectiveness of our method is evaluated by the accuracy, precision, recall, and F-measure; these results are compared with some of works recently published on the same image dataset. It shows that SIR-DL effectively solves the problem of semantic-based image retrieval and can be used to build multimedia systems in many different fields.
35
徐, 海蛟. "Deep Learning Based Semantic Scene Image Retrieval." Computer Science and Application 09, no. 08 (2019): 1561–68. http://dx.doi.org/10.12677/csa.2019.98175.
Full text
36
Sharma, Amit, Dr V. K. Singh, and Dr Pushpendra Singh. "Deep CNN Based Hybrid Model for Image Retrieval." International Journal of Innovative Technology and Exploring Engineering 11, no. 9 (2022): 23–28. http://dx.doi.org/10.35940/ijitee.g9203.0811922.
Full textAbstract:
The popularity of deep features based image retrieval and classification task has grown a lot in the recent years. Feature representation based on Convolutional Neural Networks (CNNs) found to be very effective in terms of accuracy by various researchers in the field of visual content based image retrieval. The features which are neutral to their domain knowledge with automatic learning capability from their images are in demand in various image applications. For improving accuracy and expressive power, pre-trained CNN models with the use of transfer learning can be utilized by training them on huge volume of datasets. In this paper, a hybrid model for image retrieval is being proposed by using pre-trained values of hyper parameters as input learning parameters. The performance of the model is being compared with existing pre-trained models showing higher performance on precision and recall parameters
37
Chen, Dechao, Yang Chen, Jieming Ma, et al. "An Ensemble Deep Neural Network for Footprint Image Retrieval Based on Transfer Learning." Journal of Sensors 2021 (March 16, 2021): 1–9. http://dx.doi.org/10.1155/2021/6631029.
Full textAbstract:
As one of the essential pieces of evidence of crime scenes, footprint images cannot be ignored in the cracking of serial cases. Traditional footprint comparison and retrieval require much time and human resources, significantly affecting the progress of the case. With the rapid development of deep learning, the convolutional neural network has shown excellent performance in image recognition and retrieval. To meet the actual needs of public security footprint image retrieval, we explore the effect of convolution neural networks on footprint image retrieval and propose an ensemble deep neural network for image retrieval based on transfer learning. At the same time, based on edge computing technology, we developed a footprint acquisition system to collect footprint data. Experimental results on the footprint dataset we built show that our approach is useful and practical.
38
Singh, Apoorva, Husanbir Pannu, and Avleen Malhi. "Explainable information retrieval using deep learning for medical images." Computer Science and Information Systems 19, no. 1 (2022): 277–307. http://dx.doi.org/10.2298/csis201030049s.
Full textAbstract:
Image segmentation is useful to extract valuable information for an efficient analysis on the region of interest. Mostly, the number of images generated from a real life situation such as streaming video, is large and not ideal for traditional segmentation with machine learning algorithms. This is due to the following factors (a) numerous image features (b) complex distribution of shapes, colors and textures (c) imbalance data ratio of underlying classes (d) movements of the camera, objects and (e) variations in luminance for site capture. So, we have proposed an efficient deep learning model for image classification and the proof-of-concept has been the case studied on gastrointestinal images for bleeding detection. The Explainable Artificial Intelligence (XAI) module has been utilised to reverse engineer the test results for the impact of features on a given test dataset. The architecture is generally applicable in other areas of image classification. The proposed method has been compared with state-of-the-art including Logistic Regression, Support Vector Machine, Artificial Neural Network and Random Forest. It has reported F1 score of 0.76 on the real world streaming dataset which is comparatively better than traditional methods.
39
M, Bhavya, Sai Dhanush VR, Mukunda M, and Surya J. "StegoFace - Deep Learning-Based ID Image Security." International Journal for Research in Applied Science and Engineering Technology 13, no. 3 (2025): 2373–79. https://doi.org/10.22214/ijraset.2025.67795.
Full textAbstract:
Abstract: Identity verification processes predominantly depend on photo ID cards, which are at risk of fraudulent modifications and photo substitution methods. Conventional security techniques such as watermarks, microtext, and biometric verification exhibit limitations, rendering ID images vulnerable to tampering. To tackle this challenge, we introduce StegoFace, a steganographic model based on deep learning that improves the security of ID images by embedding concealed authentication data within facial images. The system utilizes Deep Convolutional Neural Networks (CNNs), Binary Error-Correcting Codes (BECC), and an autoencoder-decoder framework to ensure the secure embedding and retrieval of data while maintaining the integrity of the image. The Recurrent Proposal Network (RPN) effectively identifies facial areas for accurate message embedding, improving tamper detection and resilience against noise and compression. Experimental findings indicate that StegoFace successfully hides and retrieves concealed messages with minimal visual distortion, offering a strong, scalable, and cost-effective approach for secure identity verification in government-issued IDs, travel documents, and access control systems.
40
Visitsattapongse, Sarinporn, Kitsada Thadson, Suejit Pechprasarn, and Nuntachai Thongpance. "Analysis of Deep Learning-Based Phase Retrieval Algorithm Performance for Quantitative Phase Imaging Microscopy." Sensors 22, no. 9 (2022): 3530. http://dx.doi.org/10.3390/s22093530.
Full textAbstract:
Quantitative phase imaging has been of interest to the science and engineering community and has been applied in multiple research fields and applications. Recently, the data-driven approach of artificial intelligence has been utilized in several optical applications, including phase retrieval. However, phase images recovered from artificial intelligence are questionable in their correctness and reliability. Here, we propose a theoretical framework to analyze and quantify the performance of a deep learning-based phase retrieval algorithm for quantitative phase imaging microscopy by comparing recovered phase images to their theoretical phase profile in terms of their correctness. This study has employed both lossless and lossy samples, including uniform plasmonic gold sensors and dielectric layer samples; the plasmonic samples are lossy, whereas the dielectric layers are lossless. The uniform samples enable us to quantify the theoretical phase since they are established and well understood. In addition, a context aggregation network has been employed to demonstrate the phase image regression. Several imaging planes have been simulated serving as input and the label for network training, including a back focal plane image, an image at the image plane, and images when the microscope sample is axially defocused. The back focal plane image plays an essential role in phase retrieval for the plasmonic samples, whereas the dielectric layer requires both image plane and back focal plane information to retrieve the phase profile correctly. Here, we demonstrate that phase images recovered using deep learning can be robust and reliable depending on the sample and the input to the deep learning.
41
Priya Vij, Dalip. "Performance Evaluation of Enhanced Deduplication Model with Image Augmentation using Deep Learning (IDME-IR)." Journal of Information Systems Engineering and Management 10, no. 16s (2025): 19–31. https://doi.org/10.52783/jisem.v10i16s.2557.
Full textAbstract:
This study aims to evaluate the performance of the Image Duplicate Matching and Elimination - Image Retrieval (IDME-IR) Deduplication Model and an image augmentation method for image retrieval across key parameters such as accuracy, precision, recall, and F1-score. The IDME-IR Deduplication Model focuses on eliminating redundant or near-duplicate images from large datasets, ensuring a cleaner and more efficient retrieval process. Meanwhile, image augmentation techniques are employed to enhance dataset diversity, improving the robustness of retrieval systems by simulating real-world variations in lighting, orientation, and noise. Both methods are evaluated within the context of image retrieval tasks, with the performance metrics being computed across various datasets. After Evaluating the Performance of IDME-IR with Image Augmentation we get accuracy 93.55%, Precision 92.1%, F1-Score 92.7% and Recall 93%. Similarly, without applying image augmentation techniques the result has been observed as accuracy 84.2%, Precision 85.3%, F1-Score 84.7% and Recall 85.4%.
42
Shazuli, Syed Ibrahim Syed Mahamood, and Arunachalam Saravanan. "Improved Whale Optimization Algorithm with Deep Learning-Driven Retinal Fundus Image Grading and Retrieval." Engineering, Technology & Applied Science Research 13, no. 5 (2023): 11555–60. http://dx.doi.org/10.48084/etasr.6111.
Full textAbstract:
Several Deep Learning (DL) and medical image Machine Learning (ML) methods have been investigated for efficient data representations of medical images, such as image classification, Content-Based Image Retrieval (CBIR), and image segmentation. CBIR helps medical professionals make decisions by retrieving similar cases and images from electronic medical image databases. CBIR needs expressive data representations for similar image identification and knowledge discovery in massive medical image databases explored by distinct algorithmic methods. In this study, an Improved Whale Optimization Algorithm with Deep Learning-Driven Retinal Fundus Image Grading and Retrieval (IWOADL-RFIGR) approach was developed. The presented IWOADL-RFIGR method mainly focused on retrieving and classifying retinal fundus images. The proposed IWOADL-RFIGR method used the Bilateral Filtering (BF) method to preprocess the retinal images, a lightweight Convolutional Neural Network (CNN) based on scratch learning with Euclidean distance-based similarity measurement for image retrieval, and the Least Square Support Vector Machine (LS-SVM) model for image classification. Finally, the IWOA was used as a hyperparameter optimization technique to improve overall performance. The experimental validation of the IWOADL-RFIGR model on a benchmark dataset exhibited better performance than other models.
43
Mahmoud, Sawsan M., Hanan A. S. Al-Jubouri, and Tawfeeq E. Abdoulabbas. "Chest Radiographs Images Retrieval Using Deep Learning Networks." Bulletin of Electrical Engineering and Informatics 11, no. 3 (2022): 1358–69. http://dx.doi.org/10.11591/eei.v11i3.3478.
Full textAbstract:
Chest diseases are among the most common diseases today. More than one million people with pneumonia enter the hospital, and about 50,000 people die annually in the U.S. alone. Also, Coronavirus disease (COVID-19) is a risky disease that threatens the health by affecting the lungs of many people around the world. Chest X-ray and CT-scan images are the radiological imaging that can be helpful to detect COVID-19. A radiologist would need to compare a patient's image with the most similar images. Content-based image retrieval in terms of medical images offers such a facility based on visual feature descriptor and similarity measurements. In this paper, a retrieval algorithm was developed to tackle such challenges based on deep convolutional neural networks (e.g., ResNet-50, AlexNet, and GoogleNet) to produce an effective feature descriptor. Also, similarity measures such as City block and Cosine were employed to compare two images. Chest X-ray and CT-scan datasets used to evaluate the proposed algorithms with a highest performance applying ResNet -50 (99% COVID-19 (+) and 98% COVID-19 (–)) and GoogleNet (84% COVID-19 (+) and 81% COVID-19 (–)) for X-ray and CT-scan respectively. The percentage increased about 1-4% when voting was used by a k-nearest neighbor classifier
44
Sawsan, M. Mahmoud, A. S. Al-Jubouri Hanan, and E. Abdoulabbas Tawfeeq. "Chest radiographs images retrieval using deep learning networks." Bulletin of Electrical Engineering and Informatics 11, no. 3 (2022): 1358~1369. https://doi.org/10.11591/eei.v11i3.3478.
Full textAbstract:
Chest diseases are among the most common diseases today. More than one million people with pneumonia enter the hospital, and about 50,000 people die annually in the U.S. alone. Also, Coronavirus disease (COVID-19) is a risky disease that threatens the health by affecting the lungs of many people around the world. Chest X-ray and CT-scan images are the radiological imaging that can be helpful to detect COVID-19. A radiologist would need to compare a patient's image with the most similar images. Content-based image retrieval in terms of medical images offers such a facility based on visual feature descriptor and similarity measurements. In this paper, a retrieval algorithm was developed to tackle such challenges based on deep convolutional neural networks (e.g., ResNet-50, AlexNet, and GoogleNet) to produce an effective feature descriptor. Also, similarity measures such as City block and Cosine were employed to compare two images. Chest X-ray and CT-scan datasets used to evaluate the proposed algorithms with a highest performance applying ResNet -50 (99% COVID-19 (+) and 98% COVID-19 (–)) and GoogleNet (84% COVID-19 (+) and 81% COVID-19 (– )) for X-ray and CT-scan respectively. The percentage increased about 1-4% when voting was used by a k-nearest neighbor classifier.
45
Wu, Gangao, Enhui Jin, Yanling Sun, Bixia Tang, and Wenming Zhao. "Deep Attention Fusion Hashing (DAFH) Model for Medical Image Retrieval." Bioengineering 11, no. 7 (2024): 673. http://dx.doi.org/10.3390/bioengineering11070673.
Full textAbstract:
In medical image retrieval, accurately retrieving relevant images significantly impacts clinical decision making and diagnostics. Traditional image-retrieval systems primarily rely on single-dimensional image data, while current deep-hashing methods are capable of learning complex feature representations. However, retrieval accuracy and efficiency are hindered by diverse modalities and limited sample sizes. Objective: To address this, we propose a novel deep learning-based hashing model, the Deep Attention Fusion Hashing (DAFH) model, which integrates advanced attention mechanisms with medical imaging data. Methods: The DAFH model enhances retrieval performance by integrating multi-modality medical imaging data and employing attention mechanisms to optimize the feature extraction process. Utilizing multimodal medical image data from the Cancer Imaging Archive (TCIA), this study constructed and trained a deep hashing network that achieves high-precision classification of various cancer types. Results: At hash code lengths of 16, 32, and 48 bits, the model respectively attained Mean Average Precision (MAP@10) values of 0.711, 0.754, and 0.762, highlighting the potential and advantage of the DAFH model in medical image retrieval. Conclusions: The DAFH model demonstrates significant improvements in the efficiency and accuracy of medical image retrieval, proving to be a valuable tool in clinical settings.
46
Amit, Sharma, V.K. Singh Dr., and Pushpendra Singh Dr. "Deep CNN Based Hybrid Model for Image Retrieval." International Journal of Innovative Technology and Exploring Engineering (IJITEE) 11, no. 9 (2023): 23–28. https://doi.org/10.35940/ijitee.G9203.0811922.
Full textAbstract:
<strong>Abstract: </strong>The popularity of deep features based image retrieval and classification task has grown a lot in the recent years. Feature representation based on Convolutional Neural Networks (CNNs) found to be very effective in terms of accuracy by various researchers in the field of visual content based image retrieval. The features which are neutral to their domain knowledge with automatic learning capability from their images are in demand in various image applications. For improving accuracy and expressive power, pre-trained CNN models with the use of transfer learning can be utilized by training them on huge volume of datasets. In this paper, a hybrid model for image retrieval is being proposed by using pre-trained values of hyper parameters as input learning parameters. The performance of the model is being compared with existing pre-trained models showing higher performance on precision and recall parameters.
47
Hama, Kenta, Takashi Matsubara, Kuniaki Uehara, and Jianfei Cai. "Exploring Uncertainty Measures for Image-caption Embedding-and-retrieval Task." ACM Transactions on Multimedia Computing, Communications, and Applications 17, no. 2 (2021): 1–19. http://dx.doi.org/10.1145/3425663.
Full textAbstract:
With the significant development of black-box machine learning algorithms, particularly deep neural networks, the practical demand for reliability assessment is rapidly increasing. On the basis of the concept that “Bayesian deep learning knows what it does not know,” the uncertainty of deep neural network outputs has been investigated as a reliability measure for classification and regression tasks. By considering an embedding task as a regression task, several existing studies have quantified the uncertainty of embedded features and improved the retrieval performance of cutting-edge models by model averaging. However, in image-caption embedding-and-retrieval tasks, well-known samples are not always easy to retrieve. This study shows that the existing method has poor performance in reliability assessment and investigates another aspect of image-caption embedding-and-retrieval tasks. We propose posterior uncertainty by considering the retrieval task as a classification task, which can accurately assess the reliability of retrieval results. The consistent performance of the two uncertainty measures is observed with different datasets (MS-COCO and Flickr30k), different deep-learning architectures (dropout and batch normalization), and different similarity functions. To the best of our knowledge, this is the first study to perform a reliability assessment on image-caption embedding-and-retrieval tasks.
48
Heri, Prasetyo, and Arie Putra Akardihas Berton. "Batik image retrieval using convolutional neural network." TELKOMNIKA Telecommunication, Computing, Electronics and Control 17, no. 6 (2019): 3010–18. https://doi.org/10.12928/TELKOMNIKA.v17i6.12701.
Full textAbstract:
This paper presents a simple technique for performing Batik image retrieval using the Convolutional Neural Network (CNN) approach. Two CNN models, i.e. supervised and unsupervised learning approach, are considered to perform end-to-end feature extraction in order to describe the content of Batik image. The distance metrics measure the similarity between the query and target images in database based on the feature generated from CNN architecture. As reported in the experimental section, the proposed supervised CNN model achieves better performance compared to unsupervised CNN in the Batik image retrieval system. In addition, image feature composed from the proposed CNN model yields better performance compared to that of the handcrafted feature descriptor. Yet, it demonstrates the superiority performance of deep learning-based approach in the Batik image retrieval system.
49
Nisha Gupta. "A Comprehensive Analysis of Feature Extraction and Retrieval Techniques used in Content-Based Image Retrieval Systems." Journal of Information Systems Engineering and Management 10, no. 38s (2025): 1198–214. https://doi.org/10.52783/jisem.v10i38s.7158.
Full textAbstract:
In this paper, the literature review about various feature extraction methods adopted for extracting feature of query image and database images has been discussed. There are main two approaches to implement content based retrieval system. First is the conventional machine learning methods another is deep learning convolution neural network architectures. Efforts are made for detailed survey of both the machine learning and deep learning approaches for the purpose of extraction of most important salient features of images directly affecting the retrieval performance for classifying the images in particular category and finally retrieving most relevant top images.
50
Abdulsttar Lafta, Sameer, Amaal Ghazi Hamad Rafash, Noaman Ahmed Yaseen Al-Falahi, Hussein Abdulqader Hussein, and Mohanad Mahdi abdulkareem. "Secure Medical Image Retrieval Using Fast Image Processing Algorithms." Scalable Computing: Practice and Experience 25, no. 5 (2024): 4323–34. http://dx.doi.org/10.12694/scpe.v25i5.3126.
Full textAbstract:
Content Based Image Retrieval (CBIR) is a relatively new idea in the field of real-time image retrieval applications; it is a framework for retrieving pictures from diverse medical imaging sources using a variety of image-related attributes, such as color, texture, and form. Using both single and multiple input queries, CBIR processes semantic data or the same object for various class labels in the context of medical image retrieval. Due to the ambiguity of image search, optimizing the retrieval of a query picture by comparing it across numerous image sources may be problematic. The goal is to find a way to optimize the process by which requested images are retrieved from various storage locations. To effectively extract medical images, we propose a hybrid framework (consisting of deep convolution neural networks (DCNN) and the Pareto Optimization technique). In order to obtain medical pictures, a DCNN is trained on them, and then its properties and classification results are employed. Explore enhanced effective medical picture retrieval by using a Pareto optimization strategy to eliminate superfluous and dominant characteristics. When it comes to retrieving images by query from various picture archives, our method outperforms more conventional methods. Use the jargon of machine learning to propose a Novel Unsupervised Label Indexing (NULI) strategy for retrieving picture labels. To enhance the effectiveness of picture retrieval, we characterize machine learning as a matrix convex optimization using a cluster rebased matrix representation. We describe an empirical investigation on many medical picture datasets, finding that the searchbased image annotation (SBIA) schema benefits from our suggested method. As a result, CT images of the lung region are explored in this study by constructing a content-based image retrieval system using various machine learning and Artificial Intelligence techniques. Real-world applications of medical imaging are becoming more significant. Medical research facilities acquire and archive a wide variety of medical pictures digitally.