To see the other types of publications on this topic, follow the link: Improved histogram of oriented gradients (HOG).
Journal articles on the topic 'Improved histogram of oriented gradients (HOG)'
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 'Improved histogram of oriented gradients (HOG).'
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
Umar, Siyudi Shafi’I, Zaharaddeen S. Iro, Abubakar Y. Zandam, and Saifulllahi Sadi Shitu. "Accelerated Histogram of Oriented Gradients for Human Detection." Dutse Journal of Pure and Applied Sciences 9, no. 1a (2023): 44–56. http://dx.doi.org/10.4314/dujopas.v9i1a.5.
Full textAbstract:
Histogram of Oriented Gradients (HOG) is an object detection algorithm used to detect people from an image. It involves features extraction called ‘HOG descriptor’ which are used to identify a person in the image. Several operations are involved in the feature extraction process. Hence performing numerous computations in order to obtain HOG descriptors takes some considerable amount of time. This slow computation speed limits HOG’s application in real-time systems. This paper investigates HOG with a view to improve its speed, modify the feature computation process to develop a faster version of HOG and finally evaluate against existing HOG. The technique of asymptotic notation in particular Big-O notation was applied to each stage of HOG and the complexity for the binning stage was modified. This results in a HOG version with a reduced complexity from n4 to n2 thereby having an improved speed as compared to the original HOG.
2
Zhang, Li Hong, and Lin Li. "Improved Pedestrian Detection Based on Extended Histogram of Oriented Gradients." Applied Mechanics and Materials 347-350 (August 2013): 3815–20. http://dx.doi.org/10.4028/www.scientific.net/amm.347-350.3815.
Full textAbstract:
In order to further improve pedestrian detection accuracy and avoid the disadvantage of original histogram of oriented gradients (HOG), differential template, overlap ratio and normalization method and so on are improved when HOG features are extracted, then more gradient information are extracted and feature description operators can be obtained which describe human detail features better in lager image regions or detection windows. Considering speed, we select support vector machine (SVM) using linear function kernel as a classifier. Multi-scale detection technique and non maxima suppression method are employed for precisely locating the pedestrians in the image. Experiments show that the human detection system improves detection accuracy and still maintains a relatively satisfactory speed.
3
Zhang, Li Hong. "Human Detection Based on SVM and Improved Histogram of Oriented Gradients." Applied Mechanics and Materials 380-384 (August 2013): 3862–65. http://dx.doi.org/10.4028/www.scientific.net/amm.380-384.3862.
Full textAbstract:
Considering the fact that original histogram of oriented gradients (HOG) cannot extract the body local features in large image regions, its features are improved when extracted, then more gradient information are extracted and feature description operators can be obtained which describe human detail features better in lager image regions or detection windows. Considering speed, we select support vector machine (SVM) using linear function kernel as a classifier. Combining with HOG extraction and SVM training, the process includes three steps: features extraction, training and detection. Experiments show that while maintaining a relatively satisfactory speed the human detection system improves detection accuracy.
4
Zhang, Li, Weiyue Xu, Cong Shen, and Yingping Huang. "Vision-Based On-Road Nighttime Vehicle Detection and Tracking Using Improved HOG Features." Sensors 24, no. 5 (2024): 1590. http://dx.doi.org/10.3390/s24051590.
Full textAbstract:
The lack of discernible vehicle contour features in low-light conditions poses a formidable challenge for nighttime vehicle detection under hardware cost constraints. Addressing this issue, an enhanced histogram of oriented gradients (HOGs) approach is introduced to extract relevant vehicle features. Initially, vehicle lights are extracted using a combination of background illumination removal and a saliency model. Subsequently, these lights are integrated with a template-based approach to delineate regions containing potential vehicles. In the next step, the fusion of superpixel and HOG (S-HOG) features within these regions is performed, and the support vector machine (SVM) is employed for classification. A non-maximum suppression (NMS) method is applied to eliminate overlapping areas, incorporating the fusion of vertical histograms of symmetrical features of oriented gradients (V-HOGs). Finally, the Kalman filter is utilized for tracking candidate vehicles over time. Experimental results demonstrate a significant improvement in the accuracy of vehicle recognition in nighttime scenarios with the proposed method.
5
Chen, Ji, Kaiping Zhan, Qingzhou Li, et al. "Spectral clustering based on histogram of oriented gradient (HOG) of coal using laser-induced breakdown spectroscopy." Journal of Analytical Atomic Spectrometry 36, no. 6 (2021): 1297–305. http://dx.doi.org/10.1039/d1ja00104c.
Full textAbstract:
Histogram of oriented gradients (HOG) was introduced in the unsupervised spectral clustering in LIBS. After clustering, the spectra of different matrices were clearly distinguished, and the accuracy of quantitative analysis of coal was improved.
6
De Ocampo, Anton Louise Pernez, Argel Bandala, and Elmer Dadios. "Gabor-enhanced histogram of oriented gradients for human presence detection applied in aerial monitoring." International Journal of Advances in Intelligent Informatics 6, no. 3 (2020): 223. http://dx.doi.org/10.26555/ijain.v6i3.514.
Full textAbstract:
In UAV-based human detection, the extraction and selection of the feature vector are one of the critical tasks to ensure the optimal performance of the detection system. Although UAV cameras capture high-resolution images, human figures' relative size renders persons at very low resolution and contrast. Feature descriptors that can adequately discriminate between local symmetrical patterns in a low-contrast image may improve a human figures' detection in vegetative environments. Such a descriptor is proposed and presented in this paper. Initially, the acquired images are fed to a digital processor in a ground station where the human detection algorithm is performed. Part of the human detection algorithm is the GeHOG feature extraction, where a bank of Gabor filters is used to generate textured images from the original. The local energy for each cell of the Gabor images is calculated to identify the dominant orientations. The bins of conventional HOG are enhanced based on the dominant orientation index and the accumulated local energy in Gabor images. To measure the performance of the proposed features, Gabor-enhanced HOG (GeHOG) and other two recent improvements to HOG, Histogram of Edge Oriented Gradients (HEOG) and Improved HOG (ImHOG), are used for human detection on INRIA dataset and a custom dataset of farmers working in fields captured via unmanned aerial vehicle. The proposed feature descriptor significantly improved human detection and performed better than recent improvements in conventional HOG. Using GeHOG improved the precision of human detection to 98.23% in the INRIA dataset. The proposed feature can significantly improve human detection applied in surveillance systems, especially in vegetative environments.
7
Moldovanu, Simona, Lenuta Pană Toporaș, Anjan Biswas, and Luminita Moraru. "Combining Sparse and Dense Features to Improve Multi-Modal Registration for Brain DTI Images." Entropy 22, no. 11 (2020): 1299. http://dx.doi.org/10.3390/e22111299.
Full textAbstract:
A new solution to overcome the constraints of multimodality medical intra-subject image registration is proposed, using the mutual information (MI) of image histogram-oriented gradients as a new matching criterion. We present a rigid, multi-modal image registration algorithm based on linear transformation and oriented gradients for the alignment of T2-weighted (T2w) images (as a fixed reference) and diffusion tensor imaging (DTI) (b-values of 500 and 1250 s/mm2) as floating images of three patients to compensate for the motion during the acquisition process. Diffusion MRI is very sensitive to motion, especially when the intensity and duration of the gradient pulses (characterized by the b-value) increases. The proposed method relies on the whole brain surface and addresses the variability of anatomical features into an image stack. The sparse features refer to corners detected using the Harris corner detector operator, while dense features use all image pixels through the image histogram of oriented gradients (HOG) as a measure of the degree of statistical dependence between a pair of registered images. HOG as a dense feature is focused on the structure and extracts the oriented gradient image in the x and y directions. MI is used as an objective function for the optimization process. The entropy functions and joint entropy function are determined using the HOGs data. To determine the best image transformation, the fiducial registration error (FRE) measure is used. We compare the results against the MI-based intensities results computed using a statistical intensity relationship between corresponding pixels in source and target images. Our approach, which is devoted to the whole brain, shows improved registration accuracy, robustness, and computational cost compared with the registration algorithms, which use anatomical features or regions of interest areas with specific neuroanatomy. Despite the supplementary HOG computation task, the computation time is comparable for MI-based intensities and MI-based HOG methods.
8
Ou, Jianping, and Jun Zhang. "Investigation on Recognition Performance of Harvesting Robot Using Regions of Interest Histogram of Oriented Gradients Feature Based on Improved Fuzzy Least Square Support Vector Machine." Mathematical Problems in Engineering 2021 (October 6, 2021): 1–10. http://dx.doi.org/10.1155/2021/6650367.
Full textAbstract:
In order to solve the problems such as big errors, lack of universality, and too much time consuming occurred in the recognition of overlapped fruits, an improved fuzzy least square support vector machine (FLS-SVM) is established based on the fruit ROI-HOG feature. First, the RGB image is transformed into saturation and value (HSV) image, and then the regions of interest (ROI) are detected from HSV color information. Finally, the histogram of oriented gradients (HOG) feature of ROI will be used as the input of FLS-SVM pattern recognizer to realize the recognition of picking fruit. In addition, the verified FLS-SVM is used to investigate the recognition performance of harvesting robot using regions of interest histogram of oriented gradients feature. The results reveal that the vector sizes are effectively reduced and a higher detection speed is achieved without compromising accuracy relative to conventional approaches. Similarly, the detection accuracy for the learning samples, the isolated fruit, the overlapped fruit, and the background can achieve 99.50%, 96.0%, 89.9%, and 97.0%, respectively, which shows the good performance of the proposed improved ROI-HOG feature recognition method.
9
Jing Zhao, Jing Zhao. "Sports Motion Feature Extraction and Recognition Based on a Modified Histogram of Oriented Gradients with Speeded Up Robust Features." 電腦學刊 33, no. 1 (2022): 063–70. http://dx.doi.org/10.53106/199115992022023301007.
Full textAbstract:
<p>Traditional motion recognition methods can extract global features, but ignore the local features. And the obscured motion cannot be recognized. Therefore, this paper proposes a modified Histogram of oriented gradients (HOG) combining speeded up robust features (SURF) for sports motion feature extraction and recognition. This new method can fully extract the local and global features of the sports motion recognition. The new algorithm first adopts background subtraction to obtain the motion region. Direction controllable filter can effectively describe the motion edge features. The HOG feature is improved by introducing direction controllable filter to enhance the local edge information. At the same time, the K-means clustering is performed on SURF to obtain the word bag model. Finally, the fused motion features are input to support vector machine (SVM) to classify and recognize the motion features. We make comparison with the state-of-the-art methods on KTH, UCF Sports and SBU Kinect Interaction data sets. The results show that the recognition accuracy of the proposed algorithm is greatly improved.</p> <p>&nbsp;</p>
10
Bakheet, Samy, and Ayoub Al-Hamadi. "A Framework for Instantaneous Driver Drowsiness Detection Based on Improved HOG Features and Naïve Bayesian Classification." Brain Sciences 11, no. 2 (2021): 240. http://dx.doi.org/10.3390/brainsci11020240.
Full textAbstract:
Due to their high distinctiveness, robustness to illumination and simple computation, Histogram of Oriented Gradient (HOG) features have attracted much attention and achieved remarkable success in many computer vision tasks. In this paper, an innovative framework for driver drowsiness detection is proposed, where an adaptive descriptor that possesses the virtue of distinctiveness, robustness and compactness is formed from an improved version of HOG features based on binarized histograms of shifted orientations. The final HOG descriptor generated from binarized HOG features is fed to the trained Naïve Bayes (NB) classifier to make the final driver drowsiness determination. Experimental results on the publicly available NTHU-DDD dataset verify that the proposed framework has the potential to be a strong contender for several state-of-the-art baselines, by achieving a competitive detection accuracy of 85.62%, without loss of efficiency or stability.
11
Mutia, Cut, Fitri Arnia, and Rusdha Muharar. "Improving the Performance of CBIR on Islamic Women Apparels Using Normalized PHOG." Bulletin of Electrical Engineering and Informatics 6, no. 3 (2017): 271–80. http://dx.doi.org/10.11591/eei.v6i3.657.
Full textAbstract:
The designs of Islamic women apparels is dynamically changing, which can be shown by emerging of online shops selling clothing with fast updates of newest models. Traditionally, buying the clothes online can be done by querying the keywords to the retrieval system. The approach has a drawback that the keywords cannot describe the clothes designs precisely. Therefore, a searching based on content–known as content-based image retrieval (CBIR)–is required. One of the features used in CBIR is the shape. This article presents a new normalization approach to the Pyramid Histogram of Oriented Gradients (PHOG) as a mean for shape feature extraction of women Islamic clothing in a retrieval system. We refer to the proposed approach as normalized PHOG (NPHOG). The Euclidean distance measured the similarity of the clothing. The performance of the system was evaluated by using 340 clothing images, comprised of four clothing categories, 85 images for each category: blouse-pants, long dress, outerwear, and tunic. The recall and precision parameters measured the retrieval performance; the Histogram of Oriented Gradients (HOG) and PHOG were the methods for comparison. The experiments showed that NPHOG improved the HOG and PHOG performance in three clothing categories.
12
Cut, Mutia, Arnia Fitri, and Muharar Rusdha. "Improving the Performance of CBIR on Islamic Women Apparels Using Normalized PHOG." Bulletin of Electrical Engineering and Informatics 6, no. 3 (2017): 271–80. https://doi.org/10.11591/eei.v6i3.657.
Full textAbstract:
The designs of Islamic women apparels is dynamically changing, which can be shown by emerging of online shops selling clothing with fast updates of newest models. Traditionally, buying the clothes online can be done by querying the keywords to the retrieval system. The approach has a drawback that the keywords cannot describe the clothes designs precisely. Therefore, a searching based on content–known as content-based image retrieval (CBIR)–is required. One of the features used in CBIR is the shape. This article presents a new normalization approach to the Pyramid Histogram of Oriented Gradients (PHOG) as a mean for shape feature extraction of women Islamic clothing in a retrieval system. We refer to the proposed approach as normalized PHOG (NPHOG). The Euclidean distance measured the similarity of the clothing. The performance of the system was evaluated by using 340 clothing images, comprised of four clothing categories, 85 images for each category: blouse-pants, long dress, outerwear, and tunic. The recall and precision parameters measured the retrieval performance; the Histogram of Oriented Gradients (HOG) and PHOG were the methods for comparison. The experiments showed that NPHOG improved the HOG and PHOG performance in three clothing categories.
13
Thimmegowda, Thirthe Gowda Mallinathapura, and Chandrika Jayaramaiah. "Cluster-based segmentation for tobacco plant detection and classification." Bulletin of Electrical Engineering and Informatics 12, no. 1 (2023): 75–85. http://dx.doi.org/10.11591/eei.v12i1.4388.
Full textAbstract:
Tobacco is one of the major economical crops in the agriculture sector. It is essential to detect tobacco plants using unmanned aerial vehicle (UAV) images for improved crop yield and plays an important role in the early treatment of tobacco plants. The proposed research work is carried out in three phases: In the first phase, we collect images from UAV’s and apply the French Commision Internationale de l'eclairage (CIE) L*a*b colour space model as pre-processing operations and segmentation. And then two prominent motion descriptors namely histogram of flow (HOF) and motion boundary histogram (MBH) are combined with the optimal histogram of oriented gradients (HOG) descriptor for exploring optimal motion trajectory and spatial measurements. And finally, the spatial variations with respect to the scale and illumination changes are incorporated using the optimal HOG descriptor. Here both dense motion patterns and HOG are refined using hierarchical feature selection using principal component analysis (PCA). The proposed model is trained and evaluated on different tobacco UAV image datasets and done a comparative analysis of different machine learning (ML) algorithms. The proposed model achieves good performance with 95% accuracy and 92% of sensitivity.
14
T. Nagamani. "Automatic Diagnosis of Parkinson’s Disease using Handwriting Patterns." Journal of Electrical Systems 20, no. 7s (2024): 1395–405. http://dx.doi.org/10.52783/jes.3712.
Full textAbstract:
Parkinson's Disease (PD) is a neuro-degenerative syndrome characterized by motor and non-motor signs, and early detection is crucial for effective intervention. This paper presents a novel approach for PD detection using computer vision and machine learning techniques applied to Spiral-Wave handwriting analysis. The dataset comprises frontal handwritten images obtained through the Spiral-Wave test, capturing subtle motor control differences. Our methodology involves resizing images to a standardized 200x200 pixels, converting them to grayscale, and applying thresholding for improved feature abstraction. Histogram of Oriented Gradients (HOG) is employed to capture shape and texture information. The development of a strong approach for deriving significant features from Spiral-Wave handwriting patterns and the usage of machine learning classifiers for precise PD analysis are the two main goals of this work. The emphasis is on using Random Forest and K-Nearest Neighbours (KNN) classifiers for Spiral and Wave pictures, respectively, in conjunction with the Histogram of Oriented Gradients (HOG) approach for feature extraction. For Spiral images, a Random Forest Classifier is utilized, achieving an accuracy of 86.67%. The classifier's interpretability is enhanced through an analysis of feature importance, revealing critical HOG features for distinguishing between healthy and PD-afflicted patterns. The Wave images are classified using a K-Nearest Neighbours (KNN) model, attaining an accuracy of 76.67%. Performance metrics, including precision, recall, and F1-score, offer a nuanced assessment of the KNN model's capabilities.
15
Wibowo, Suryo Adhi, Hansoo Lee, Eun Kyeong Kim, and Sungshin Kim. "Convolutional Shallow Features for Performance Improvement of Histogram of Oriented Gradients in Visual Object Tracking." Mathematical Problems in Engineering 2017 (2017): 1–9. http://dx.doi.org/10.1155/2017/6329864.
Full textAbstract:
Histogram of oriented gradients (HOG) is a feature descriptor typically used for object detection. For object tracking, this feature has certain drawbacks when the target object is influenced by a change in motion or size. In this paper, the use of convolutional shallow features is proposed to improve the performance of HOG feature-based object tracking. Because the proposed method works based on a correlation filter, the response maps for each feature are summed in order to obtain the final response map. The location of the target object is then predicted based on the maximum value of the optimized final response map. Further, a model update is used to overcome the change in appearance of the target object during tracking. A performance evaluation of the proposed method is obtained by using Visual Object Tracking 2015 (VOT2015) benchmark dataset and its protocols. The results are then provided based on their accuracy-robustness (AR) rank. Furthermore, through a comparison with several state-of-the-art tracking algorithms, the proposed method was shown to achieve the highest rank in terms of accuracy and a third rank for robustness. In addition, the proposed method significantly improves the robustness of HOG-based features.
16
Fan, Tao. "Image Recognition and Simulation Based on Distributed Artificial Intelligence." Complexity 2021 (April 15, 2021): 1–11. http://dx.doi.org/10.1155/2021/5575883.
Full textAbstract:
This paper studies the traditional target classification and recognition algorithm based on Histogram of Oriented Gradients (HOG) feature extraction and Support Vector Machine (SVM) classification and applies this algorithm to distributed artificial intelligence image recognition. Due to the huge number of images, the general detection speed cannot meet the requirements. We have improved the HOG feature extraction algorithm. Using principal component analysis (PCA) to perform dimensionality reduction operations on HOG features and doing distributed artificial intelligence image recognition experiments, the results show that the image detection efficiency is slightly improved, and the detection speed is also improved. This article analyzes the reason for these changes because PCA mainly uses the useful feature information in HOG features. The parallelization processing of HOG features on graphics processing unit (GPU) is studied. GPU is used for high parallel and high-density calculations, and the calculation of HOG features is very complicated. Using GPU for parallelization of HOG features can make the calculation speed of HOG features improved. We use image experiments for the parallelized HOG feature algorithm. Experimental simulations show that the speed of distributed artificial intelligence image recognition is greatly improved. By analyzing the existing digital image recognition methods, an improved BP neural network algorithm is proposed. Under the premise of ensuring accuracy, the recognition speed of digital images is accelerated, the time required for recognition is reduced, real-time performance is guaranteed, and the effectiveness of the algorithm is verified.
17
Jafari, Farzaneh, and Anup Basu. "Saliency-Driven Hand Gesture Recognition Incorporating Histogram of Oriented Gradients (HOG) and Deep Learning." Sensors 23, no. 18 (2023): 7790. http://dx.doi.org/10.3390/s23187790.
Full textAbstract:
Hand gesture recognition is a vital means of communication to convey information between humans and machines. We propose a novel model for hand gesture recognition based on computer vision methods and compare results based on images with complex scenes. While extracting skin color information is an efficient method to determine hand regions, complicated image backgrounds adversely affect recognizing the exact area of the hand shape. Some valuable features like saliency maps, histogram of oriented gradients (HOG), Canny edge detection, and skin color help us maximize the accuracy of hand shape recognition. Considering these features, we proposed an efficient hand posture detection model that improves the test accuracy results to over 99% on the NUS Hand Posture Dataset II and more than 97% on the hand gesture dataset with different challenging backgrounds. In addition, we added noise to around 60% of our datasets. Replicating our experiment, we achieved more than 98% and nearly 97% accuracy on NUS and hand gesture datasets, respectively. Experiments illustrate that the saliency method with HOG has stable performance for a wide range of images with complex backgrounds having varied hand colors and sizes.
18
S., Subhashini, and Revathi S. "A New Fusion Feature Selection Model (FFSM) based Feature Extraction System for Hand Gesture Recognition." Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications 14, no. 4 (2023): 149–63. http://dx.doi.org/10.58346/jowua.2023.i4.011.
Full textAbstract:
The research presented here proposes a unique approach for exact feature extraction that makes use of the Fusion Feature Selection Model (FFSM). The method encompasses various stages to preprocess and extract crucial features from first-person hand action (FHPA) images. Preprocessing involves video-to-frame conversion, RGB to grayscale conversion, an improved median filter, and Gaussian blur-based image smoothing. Segmentation is achieved using the Improved SwinNet to identify meaningful regions within the images. Feature extraction employs the Gabor Line Derivative (GLD) method, Active Shape Model (ASM), and Histogram of Oriented Gradients (HOG) to capture texture, edge, and shape information, respectively. Extensive experimental evaluations demonstrate the effectiveness of our proposed approach, achieving remarkable performance in accurate feature extraction tasks.
19
Asfar, A. Muh Fitrah, Mardiyyah Hasnawi, and Herdianti Darwis. "COMBINATIONS OF FEATURE EXTRACTIONS AND MACHINE LEARNING ALGORITHMS FOR SKIN CANCER CLASSIFICATION." Jurnal Teknik Informatika (Jutif) 5, no. 6 (2024): 1591–98. https://doi.org/10.52436/1.jutif.2024.5.6.2514.
Full textAbstract:
One of the most common causes of death worldwide is skin cancer and its incidence is increasing. To achieve optimal treatment and improve clinical outcomes for patients, precision skin cancer detection and classification approaches are required, which can be achieved through the application of feature extraction and machine learning algorithms. The development of such algorithms to identify important patterns from skin cancer image datasets enables early detection and more accurate classification and more effective treatment. Although previous studies have tried to detect skin cancer using feature extraction techniques such as HFF, HOG, and GLCM, some weaknesses still need to be improved. This research aims to combine various feature extraction methods such as Gray Level Co-occurrence Matrix, Histogram Oriented Gradients, and Local Binary Patterns and machine learning algorithms such as Support Vector Machine, Random Forest, and Gaussian Naïve Bayes in the classification process between Melanoma and Nevus skin cancers. In this research, the number of datasets used is 17,397 derived from the ISIC Dataset. The results showed that the Histogram Oriented Gradients method with Support Vector Machine algorithm achieved the highest accuracy of 92%. The combination of Gray Level Co-occurrence Matrix and Local Binary Patterns with Random Forest algorithm also achieved an accuracy of 92%, the combination of Gray Level Co-occurrence Matrix, Histogram Oriented Gradients, and Local Binary Patterns with Random Forest algorithm also resulted in an accuracy of 92%. These findings suggest that the combination of various feature extraction methods and machine learning algorithms can improve accuracy in skin cancer classification, which in turn can contribute to early detection and more effective treatment.
20
J, Sujanaa, and Palanivel S. "HOG-BASED EMOTION RECOGNITION USING ONE-DIMENSIONAL CONVOLUTIONAL NEURAL NETWORK." ICTACT Journal on Image and Video Processing 11, no. 2 (2020): 2310–15. https://doi.org/10.21917/ijivp.2020.0328.
Full textAbstract:
This work proposes an emotion detection approach using Histogram of Oriented Gradients algorithm. Emotion detection is a crucial area since the emotions are extremely person dependent and finding them is hard with various lightning and illumination changes. Most of the works in this field focus on predicting the emotion using the facial region. In the proposed work, emotion detection is done using the mouth region. The dataset is comprised of mouth images containing emotions such as happy, normal and surprised in the form of video frames. The mouth regions are detected using the Haar-Based Cascade classifier at 20 frames per second. The HOG features are then extracted to detect three emotions namely Happy, Normal and Surprised. These HOG features are then trained using One-Dimensional Convolutional Neural Network (1D-CNN). The experimental results show that the proposed system can identify the emotions which gave improved performance than the earlier works.
21
S, Sathyapriya, and Anitha D. "Dynamic mutation based glowworm swarm optimization with long short-term memory approaches for thyroid nodule classification." Indian Journal of Science and Technology 13, no. 14 (2020): 1523–34. https://doi.org/10.17485/IJST/v13i14.38.
Full textAbstract:
Abstract <strong>Objectives:</strong> To design an efficient approach for thyroid nodule classification with higher true positive rate. <strong>Methodology and statistical analysis:</strong> The proposed system designed as a Dynamic Mutation based Glowworm Swarm Optimization with Long-Short Term Memory (DMGSO with LSTM) scheme for thyroid nodule classification. In this proposed research work, input thyroid images are preprocessed by using Dynamically Weighted Median Filter (DWMF). The preprocessed images are segmented with the help of Region based Active Contour scheme. An Improved Local Binary Pattern (ILBP), Grey Level Cooccurrence Matrix (GLCM) and Histogram of Oriented Gradient (HOG) features are extracted from segmented image. Then the optimal features are selected by using Dynamic Mutation based Glowworm Swarm Optimization (DMGSO) algorithm. Finally, the Long-Short Term Memory (LSTM) scheme is utilized for classifying the thyroid nodule. <strong>Findings:</strong> The experimental results show that the proposed system achieves better performance compared with the existing system in terms of accuracy, precision, recall and f-measure. <strong>Keywords:</strong> Thyroid nodule; Histogram of Oriented Gradient (HOG); Long Short-Term Memory (LSTM); Dynamic Mutation based Glow worm Swarm Optimization (DMGSO)
22
ILGIN, Hakki Alparslan, Fevzi Anıl AYDEMİR, Berkay CEDİMOĞLU, Muhammet Nurullah AYDIN, and Turkey-hasan SİLLELİ. "Comparative analysis of mature tomato detection by feature extraction and machine learning for autonomous greenhouse robots." Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering 65, no. 2 (2023): 100–114. http://dx.doi.org/10.33769/aupse.1274677.
Full textAbstract:
Accurate detection of tomatoes grown in greenhouses is important for timely harvesting. In this way, it is ensured that mature tomatoes are collected by distinguishing them from the unripe ones. Insufficient light, occlusion, and overlapping adversely affect the detection of mature tomatoes. In addition, it is time consuming for people to detect mature tomatoes at certain periods in large greenhouses. For these reasons, high-performance automatic detection of tomatoes by greenhouse robots has become an increasingly studied area today. In this paper, two feature extraction methods, histogram of oriented gradients (HOG) and local binary patterns (LBP), which are effective in object recognition, and two important and commonly used classifiers of machine learning, support vector machines (SVM) and k-nearest neighbor (kNN), are comparatively used to detect and count tomatoes. The HOG and LBP features are classified separately and together by SVM or kNN, and the success of each case are compared. Performance of the detection is improved by eliminating false positive results at the postprocessing stage using color information.
23
Hasan, Zewar Fadhlilddin. "An Improved Facial Expression Recognition Method Using Combined Hog and Gabor Features." Science Journal of University of Zakho 10, no. 2 (2022): 54–59. http://dx.doi.org/10.25271/sjuoz.2022.10.2.897.
Full textAbstract:
Lately, face recognition technology has been a significant study and a topic for generations. It remains a difficult task because of the variability of wide interclass. The subject of facial expression recognition is addressed in this research using a practical method. This method can recognize the human face and it is various features such as the eyes, brows, and lips. The motions or deformations of the face muscles are the cause of facial expressions. In addition, computer vision tasks such as texture recognition and categorization are commonly used. Furthermore, feature extraction basically discovers groups of features that demonstrate an image of visual texture. It is a critical phase to complete the operation. This work extracts features utilizing Histogram of Oriented Gradients (HOG) and Gabor approaches and then combines extracted features to improve the accuracy of facial expression detection. The derived features were particularly sensitive to object deformations. Later on, the classification of facial expression is handled using (Support Vector Machine) SVM. Analyze the proposed approach on FER 2013 data to see how well it performs. The proposal has a categorization rate of 63.82% on average. The proposed technique determines the comparable classification accuracy as shown in experimental findings. To improve this work it is planned to use deep features and combined them with HOG or Gabor, as well as to show the efficiency of the work it can be implemented with more datasets such as the JAFFE database.
24
Bindu, Hima, and Manjunathachari K. "Hybrid feature descriptor and probabilistic neuro-fuzzy system for face recognition." Sensor Review 38, no. 3 (2018): 269–81. http://dx.doi.org/10.1108/sr-06-2017-0115.
Full textAbstract:
Purpose This paper aims to develop the Hybrid feature descriptor and probabilistic neuro-fuzzy system for attaining the high accuracy in face recognition system. In recent days, facial recognition (FR) systems play a vital part in several applications such as surveillance, access control and image understanding. Accordingly, various face recognition methods have been developed in the literature, but the applicability of these algorithms is restricted because of unsatisfied accuracy. So, the improvement of face recognition is significantly important for the current trend. Design/methodology/approach This paper proposes a face recognition system through feature extraction and classification. The proposed model extracts the local and the global feature of the image. The local features of the image are extracted using the kernel based scale invariant feature transform (K-SIFT) model and the global features are extracted using the proposed m-Co-HOG model. (Co-HOG: co-occurrence histograms of oriented gradients) The proposed m-Co-HOG model has the properties of the Co-HOG algorithm. The feature vector database contains combined local and the global feature vectors derived using the K-SIFT model and the proposed m-Co-HOG algorithm. This paper proposes a probabilistic neuro-fuzzy classifier system for the finding the identity of the person from the extracted feature vector database. Findings The face images required for the simulation of the proposed work are taken from the CVL database. The simulation considers a total of 114 persons form the CVL database. From the results, it is evident that the proposed model has outperformed the existing models with an improved accuracy of 0.98. The false acceptance rate (FAR) and false rejection rate (FRR) values of the proposed model have a low value of 0.01. Originality/value This paper proposes a face recognition system with proposed m-Co-HOG vector and the hybrid neuro-fuzzy classifier. Feature extraction was based on the proposed m-Co-HOG vector for extracting the global features and the existing K-SIFT model for extracting the local features from the face images. The proposed m-Co-HOG vector utilizes the existing Co-HOG model for feature extraction, along with a new color gradient decomposition method. The major advantage of the proposed m-Co-HOG vector is that it utilizes the color features of the image along with other features during the histogram operation.
25
Lahiani, Houssem, and Mahmoud Neji. "Design of a Hand Pose Recognition System for Mobile and Embedded Devices." International Journal of Recent Contributions from Engineering, Science & IT (iJES) 10, no. 04 (2022): 17–31. http://dx.doi.org/10.3991/ijes.v10i04.35163.
Full textAbstract:
Today, smart devices such smart watches and smart cell phones are becoming ever-present in all fields that influence the quality of life of the modern people. These on-board systems have revolutionized the behavior of human beings and especially their way of communicating. In this context and to improve the experience of using these devices, we aim to develop a system that recognizes hand poses in the air by a smart device. In this work, the system is based on Histogram of Oriented Gradient (HOG) features and Support Vector Machine (SVM) classifier. The impact of using HOG and SVM on mobile devices is studied. To carry out this study, we used an improved version of the "NUS I" dataset and obtained a recognition rate of approximately 94%. In addition, we conducted run speed experiments on various mobile devices to study the impact of this task on this embedded platform. The main contribution of this work is to test the impact of using the HOG descriptor and the SVM classifier in terms of recognition rate and execution time on low-end smartphones.Today, smart devices such smart watches and smart cell phones are becoming ever-present in all fields that influence the quality of life of the modern people. These on-board systems have revolutionized the behavior of human beings and especially their way of communicating. In this context and to improve the experience of using these devices, we aim to develop a system that recognizes hand poses in the air by a smart device. In this work, the system is based on Histogram of Oriented Gradient (HOG) features and Support Vector Machine (SVM) classifier. The impact of using HOG and SVM on mobile devices is studied. To carry out this study, we used an improved version of the "NUS I" dataset and obtained a recognition rate of approximately 94%. In addition, we conducted run speed experiments on various mobile devices to study the impact of this task on this embedded platform. The main contribution of this work is to test the impact of using the HOG descriptor and the SVM classifier in terms of recognition rate and execution time on low-end smartphones.
26
Chen, Guo-Hong, Jie Ni, Zhuo Chen, et al. "Detection of Highway Pavement Damage Based on a CNN Using Grayscale and HOG Features." Sensors 22, no. 7 (2022): 2455. http://dx.doi.org/10.3390/s22072455.
Full textAbstract:
Aiming at the demand for rapid detection of highway pavement damage, many deep learning methods based on convolutional neural networks (CNNs) have been developed. However, CNN methods with raw image data require a high-performance hardware configuration and cost machine time. To reduce machine time and to apply the detection methods in common scenarios, the CNN structure with preprocessed image data needs to be simplified. In this work, a detection method based on a CNN and the combination of the grayscale and histogram of oriented gradients (HOG) features is proposed. First, the Gamma correction was employed to highlight the grayscale distribution of the damage area, which compresses the space of normal pavement. The preprocessed image was then divided into several unit cells, whose grayscale and HOG were calculated, respectively. The grayscale and HOG of each unit cell were combined to construct the grayscale-weighted HOG (GHOG) feature patterns. These feature patterns were input to the CNN with a specific structure and parameters. The trained indices suggested that the performance of the GHOG-based method was significantly improved, compared with the traditional HOG-based method. Furthermore, the GHOG-feature-based CNN technique exhibited flexibility and effectiveness under the same accuracy, in comparison to those deep learning techniques that directly deal with raw data. Since the grayscale has a definite physical meaning, the present detection method possesses a potential application for the further detection of damage details in the future.
27
Yasir, Siddiqui Muhammad, and Hyun Kim. "Lightweight Deepfake Detection Based on Multi-Feature Fusion." Applied Sciences 15, no. 4 (2025): 1954. https://doi.org/10.3390/app15041954.
Full textAbstract:
Deepfake technology utilizes deep learning (DL)-based face manipulation techniques to seamlessly replace faces in videos, creating highly realistic but artificially generated content. Although this technology has beneficial applications in media and entertainment, misuse of its capabilities may lead to serious risks, including identity theft, cyberbullying, and false information. The integration of DL with visual cognition has resulted in important technological improvements, particularly in addressing privacy risks caused by artificially generated “deepfake” images on digital media platforms. In this study, we propose an efficient and lightweight method for detecting deepfake images and videos, making it suitable for devices with limited computational resources. In order to reduce the computational burden usually associated with DL models, our method integrates machine learning classifiers in combination with keyframing approaches and texture analysis. Moreover, the features extracted with a histogram of oriented gradients (HOG), local binary pattern (LBP), and KAZE bands were integrated to evaluate using random forest, extreme gradient boosting, extra trees, and support vector classifier algorithms. Our findings show a feature-level fusion of HOG, LBP, and KAZE features improves accuracy to 92% and 96% on FaceForensics++ and Celeb-DF(v2), respectively.
28
Jamil, Adeel Ahmad, Fawad Hussain, Muhammad Haroon Yousaf, Ammar Mohsin Butt, and Sergio A. Velastin. "Vehicle Make and Model Recognition using Bag of Expressions." Sensors 20, no. 4 (2020): 1033. http://dx.doi.org/10.3390/s20041033.
Full textAbstract:
Vehicle make and model recognition (VMMR) is a key task for automated vehicular surveillance (AVS) and various intelligent transport system (ITS) applications. In this paper, we propose and study the suitability of the bag of expressions (BoE) approach for VMMR-based applications. The method includes neighborhood information in addition to visual words. BoE improves the existing power of a bag of words (BOW) approach, including occlusion handling, scale invariance and view independence. The proposed approach extracts features using a combination of different keypoint detectors and a Histogram of Oriented Gradients (HOG) descriptor. An optimized dictionary of expressions is formed using visual words acquired through k-means clustering. The histogram of expressions is created by computing the occurrences of each expression in the image. For classification, multiclass linear support vector machines (SVM) are trained over the BoE-based features representation. The approach has been evaluated by applying cross-validation tests on the publicly available National Taiwan Ocean University-Make and Model Recognition (NTOU-MMR) dataset, and experimental results show that it outperforms recent approaches for VMMR. With multiclass linear SVM classification, promising average accuracy and processing speed are obtained using a combination of keypoint detectors with HOG-based BoE description, making it applicable to real-time VMMR systems.
29
Xu, Hu, Yang Yu, Xiaomin Zhang, and Ju He. "Cross-Granularity Infrared Image Segmentation Network for Nighttime Marine Observations." Journal of Marine Science and Engineering 12, no. 11 (2024): 2082. http://dx.doi.org/10.3390/jmse12112082.
Full textAbstract:
Infrared image segmentation in marine environments is crucial for enhancing nighttime observations and ensuring maritime safety. While recent advancements in deep learning have significantly improved segmentation accuracy, challenges remain due to nighttime marine scenes including low contrast and noise backgrounds. This paper introduces a cross-granularity infrared image segmentation network CGSegNet designed to address these challenges specifically for infrared images. The proposed method designs a hybrid feature framework with cross-granularity to enhance segmentation performance in complex water surface scenarios. To suppress feature semantic disparity against different feature granularity, we propose an adaptive multi-scale fusion module (AMF) that combines local granularity extraction with global context granularity. Additionally, incorporating a handcrafted histogram of oriented gradients (HOG) features, we designed a novel HOG feature fusion module to improve edge detection accuracy under low-contrast conditions. Comprehensive experiments conducted on the public infrared segmentation dataset demonstrate that our method outperforms state-of-the-art techniques, achieving superior segmentation results compared to professional infrared image segmentation methods. The results highlight the potential of our approach in facilitating accurate infrared image segmentation for nighttime marine observation, with implications for maritime safety and environmental monitoring.
30
Savade, Gaurav R. "Automatic Target Detection using Ground Penetrating Radar (GPR) Data Based on a Machine Learning Approach." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 02 (2025): 1–9. https://doi.org/10.55041/ijsrem41437.
Full textAbstract:
Automatic target classification in radar-based systems is critical for various applications, including defense, surveillance, and environmental monitoring. This research presents a robust approach for classifying targets in ground-penetrating radar (GPR) data by combining texture-based Haralick features and shape-oriented Histogram of Oriented Gradients (HOG) features. The integration of these complementary feature sets enhances target characterization by capturing both spatial textures and edge patterns in GPR images. Using the extracted features, we evaluate two prominent machine learning classifiers, Support Vector Machine (SVM) and Random Forest (RF), for their classification accuracy, precision, and computational efficiency. Experimental results on a benchmark GPR dataset show that the fusion of Haralick and HOG features significantly improves classification performance compared to individual feature sets. The SVM classifier achieves superior accuracy with 95.83% in predicting the target/non-target object as mine/non-mine. Further, mine target is detected with image annotation using image morphology. Our method highlights the potential of hybrid feature extraction and machine learning classifiers in achieving accurate and reliable automatic target classification in GPR data, paving the way for real-time applications in complex operational environments. Key Words: Machine Learning, Ground Penetrating Radar, Object Detection, Signal Processing.
31
Patil, Shivanand Μ., V. S. Malemath, Suman Muddapur, and Praveen M. Dhulavvagol. "Enhanced Text Detection in Natural Scenes using Advanced Machine Learning Techniques." Engineering, Technology & Applied Science Research 15, no. 2 (2025): 22114–18. https://doi.org/10.48084/etasr.10029.
Full textAbstract:
Text detection in natural scenes remains a fundamental challenge in computer vision, impacting applications from mobile navigation to document digitization. Traditional methods struggle with varying text orientations, complex backgrounds, and inconsistent lighting, while recent deep-learning approaches face computational efficiency challenges. This paper presents a novel hybrid machine-learning framework that combines traditional computer vision with advanced machine learning to achieve robust text detection. The framework integrates optimized preprocessing techniques, feature extraction methods, including Histogram Oriented Gradients (HOG) and Maximally Stable Extremal Regions (MSER), and a lightweight convolutional neural network for improved accuracy and efficiency. Experimental evaluation on benchmark datasets demonstrates superior performance, achieving 98% precision, 97.5% recall, and 97.8% F1-score, while maintaining real-time processing capabilities at 45 fps. The framework significantly outperforms existing methods in handling diverse text scenarios, establishing a new standard for natural scene text detection. This research contributes to the advancement of text detection technology and offers practical applications in augmented reality, autonomous navigation, and document processing systems.
32
Krishna, R. Ramya, and N. Jyothi. "Road Surface Condition Identification with Deep Neural Networks and SVM Classifier." Engineering, Technology & Applied Science Research 15, no. 2 (2025): 21998–2003. https://doi.org/10.48084/etasr.10166.
Full textAbstract:
Roads are people's main transportation mode, deeming them an important aspect of worldwide everyday life. However, weather conditions increasingly impact road infrastructure, necessitating improved road safety measures. Identifying road types enhances traffic management and safety, particularly as roads often sustain damage during the rainy season and require restoration that takes time. In many countries, weather conditions also affect road usability. This study proposes a Deep Neural Network (DNN) for automatic road classification Road Surface Images (RSI). ResNet-50 is employed for feature extraction, while additional features, such as Gray-Level Co-Occurrence Matrix (GLCM), correlation factor, and Histogram of Oriented Gradients (HOG) are integrated to improve detection accuracy. These features collectively form the GHR50 model. Next, the collected features are classified using a Support Vector Machine (SVM) classifier and the parameters are evaluated. The proposed GHR50 model achieves 97.39% accuracy in detecting road types, such as dry mud, fresh snow, and water-asphalt smooth, representing a 0.95% improvement over conventional Convolutional Neural Networks (CNNs).
33
Guo, Yong De, Zhi Gang Xie, and Hong Bing Ma. "Pedestrian Detection Optimization Algorithm Based on Low-Altitude UAV." Applied Mechanics and Materials 571-572 (June 2014): 757–63. http://dx.doi.org/10.4028/www.scientific.net/amm.571-572.757.
Full textAbstract:
Pedestrian detection is one of the critical benchmarks for object detection in computer vision. In recent years, more effective detectors and features, such as Histograms of Oriented Gradients (HOG) have been proposed. The process of HOG features calculation is slow, and the features cannot satisfy represent the human body. Therefore, we adopt the multi-channel features, and propose a new improved method for accelerated integral image, the execution time of which is less than the original method. In addition, we apply novel multi-scales detection to detect new scenario, which is based on the low-altitude UAV. Under such scenario our algorithm can handle the changing in pedestrian posture and occlusion cues. The experimental results indicate that our algorithm is rapid and efficient under dynamic camera, comparing with other methods in INRIA dataset.
34
Muhammad Aiman Irfan Shahrel, Raihani Mohamed, Sufri Muhammad, Ade Candra, and Muhammad Noorazlan Shah Zainudin. "Enhancing Smart Home Security System with HOG Algorithm." Journal of Advanced Research in Applied Sciences and Engineering Technology 64, no. 4 (2025): 187–200. https://doi.org/10.37934/araset.64.4.187200.
Full textAbstract:
The escalating global concern over burglary incidents, particularly by the economic repercussions of the 2020 pandemic, necessitates innovative solutions to fortify residential security. Traditional locks, once presumed as the primary defence against intruders, have proven inadequate against modern burglary techniques. This work proposes the development and implementation of a "Smart Home Security System" to address the imperative need for improved home security. By implementing technologies such as the Internet of Things (IoT), artificial intelligence (AI), and mobile applications, the proposed system aims to establish multiple layers of protection against unauthorized entry. The objectives of this study revolve around the integration of various components, including smart locks employing solenoid locking mechanisms, ultrasonic sensors, video surveillance, and mobile application-based access control. The system offers diverse methods for unlocking, encompassing passcodes, face recognition utilizing the HOG (Histogram of Oriented Gradients) algorithm, mobile applications, and physical button switches. Leveraging Firebase for database management enhances system reliability and accessibility. Additionally, the Smart Home Security System incorporates important features such as real-time monitoring of the front door and image capture capabilities. Furthermore, a burglary detection system, facilitated by ultrasonic sensors, serves as a proactive measure against unauthorized access attempts. A key goal of the proposed Smart Home Security System is to offer homeowners an advanced and comprehensive security solution at a lower cost, while maintaining functionality superior to existing systems on the market. By integrating cutting-edge technology and cost-effective components, this system provides a robust and accessible defense mechanism, empowering homeowners with enhanced protection against contemporary burglary threats.
35
Bastiaans, Jessica Carmelita, James Hartojo, Ricardus Anggi Pramunendar, and Pulung Nurtantio Andono. "Evaluating the Impact of Particle Swarm Optimization Based Feature Selection on Support Vector Machine Performance in Coral Reef Health Classification." IJNMT (International Journal of New Media Technology) 11, no. 2 (2025): 90–99. https://doi.org/10.31937/ijnmt.v11i2.3761.
Full textAbstract:
This research explores improving coral reef image classification accuracy by combining Histogram of Oriented Gradients (HOG) feature extraction, image classification with Support Vector Machine (SVM), and feature selection with Particle Swarm Optimization (PSO). Given the ecological importance of coral reefs and the threats they face, accurate classification of coral reef health is essential for conservation efforts. This study used healthy, whitish, and dead coral reef datasets divided into training, validation, and test data. The proposed approach successfully improved the classification accuracy significantly, reaching 85.44% with the SVM model optimized by PSO, compared to 79.11% in the original SVM model. PSO not only improves accuracy but also reduces running time, demonstrating its effectiveness and computational efficiency. The results of this study highlight the potential of PSO in optimizing machine learning models, especially in complex image classification tasks. While the results obtained are promising, the study acknowledges several limitations, including the need for further validation with larger and more diverse datasets to ensure model robustness and generalizability. This research contributes to the field of marine ecology by providing a more accurate and efficient coral reef classification method, which can be applied to other image classifications.
36
Bohush, Rykhard, Sergey Ablameyko, Tatiana Kalganova, and Pavel Yarashevich. "Extraction of image parking spaces in intelligent video surveillance systems." Machine Graphics and Vision 27, no. 1/4 (2019): 47–62. http://dx.doi.org/10.22630/mgv.2018.27.1.3.
Full textAbstract:
This paper discusses the algorithmic framework for image parking lot localization and classification for the video intelligent parking system. Perspective transformation, adaptive Otsu's binarization, mathematical morphology operations, representation of horizontal lines as vectors, creating and filtering vertical lines, and parking space coordinates determination are used for the localization of parking spaces in a~video frame. The algorithm for classification of parking spaces is based on the Histogram of Oriented Descriptors (HOG) and the Support Vector Machine (SVM) classifier. Parking lot descriptors are extracted based on HOG. The overall algorithmic framework consists of the following steps: vertical and horizontal gradient calculation for the image of the parking lot, gradient module vector and orientation calculation, power gradient accumulation in accordance with cell orientations, blocking of cells, second norm calculations, and normalization of cell orientation in blocks. The parameters of the descriptor have been optimized experimentally. The results demonstrate the improved classification accuracy over the class of similar algorithms and the proposed framework performs the best among the algorithms proposed earlier to solve the parking recognition problem.
37
Ren, Yongmei, Jie Yang, Qingnian Zhang, and Zhiqiang Guo. "Multi-Feature Fusion with Convolutional Neural Network for Ship Classification in Optical Images." Applied Sciences 9, no. 20 (2019): 4209. http://dx.doi.org/10.3390/app9204209.
Full textAbstract:
The appearance of ships is easily affected by external factors—illumination, weather conditions, and sea state—that make ship classification a challenging task. To facilitate realization of enhanced ship-classification performance, this study proposes a ship classification method based on multi-feature fusion with a convolutional neural network (CNN). First, an improved CNN characterized by shallow layers and few parameters is proposed to learn high-level features and capture structural information. Second, handcrafted features of the histogram of oriented gradients (HOG) and local binary patterns (LBP) are combined with high-level features extracted by the improved CNN in the last fully connected layer to obtain discriminative feature representation. The handcrafted features supplement the edge information and spatial texture information of the ship images. Then, the Softmax function is used to classify different types of ships in the output layer. Effectiveness of the proposed method is evaluated based on its application to two datasets—one self-built and the other publicly available, called visible and infrared spectrums (VAIS). As observed, the proposed method demonstrated attainment of average classification accuracies equal to 97.50% and 93.60%, respectively, when applied to these datasets. Additionally, results obtained in terms of the F1-score and confusion matrix demonstrate the proposed method to be superior to some state-of-the-art methods.
38
Liang, Zuo Juan, Chang Xu Dong Ye, Shan Shan Zhang, and Yong Chen. "Pedestrian Detection and Tracking Based on Fast HOG and Time Varying System Particle Filter." Applied Mechanics and Materials 568-570 (June 2014): 721–25. http://dx.doi.org/10.4028/www.scientific.net/amm.568-570.721.
Full textAbstract:
Pedestrians are quite visually different at multi-scale changes and view-point variations, which are crucial factors for detection. Firstly calculations of multiscale features of HOG(Histogram of Oriented Gradient) from video images are usually based on finer scale pyramid strategy, which is to figure out low-level features respectively at each scale level. This scheme has redundent information and worse real-time performance, which become urgent bottleneck in applications. A new fast scale pyramid strategy based on feature forecast algorithm was adopted according to [1], which can speed up low-level feature calculations and solve real-time problem fundamentally. Secondly a new tracking pedestrian algorithm was proposed, which combined local LBP(Local Binary Pattern) and HOG as a model description of the pedestrian target, the tracking system equation was improved according to the non-uniform motion of the pedestrian in order to enhance the effectiveness and the guidance of the particle propagation. The final experimental results show that this method is more robust than those based on single feature.
39
Tong, Kuangwei, Zhongbin Wang, Lei Si, Chao Tan, and Peiyang Li. "A Novel Pipeline Leak Recognition Method of Mine Air Compressor Based on Infrared Thermal Image Using IFA and SVM." Applied Sciences 10, no. 17 (2020): 5991. http://dx.doi.org/10.3390/app10175991.
Full textAbstract:
In order to accurately identify the pipeline leak fault of a mine air compressor, a novel intelligent diagnosis method is presented based on the integration of an adaptive wavelet threshold denoising (WTD) algorithm, improved firefly algorithm (IFA), Otsu-Grabcut image segmentation algorithm, histogram of oriented gradient (HOG), gray-level co-occurrence matrix (GLCM) and support vector machine (SVM). In the proposed method, the adaptive step strategy and local optimal firefly self-search strategy for the basic firefly algorithm (FA) are used to improve the optimization effect. The infrared thermal image is denoised by using wavelet threshold algorithm which is optimized by IFA (WTD-IFA). The Otsu-Grabcut algorithm is used to segment the image and extract the target. The HOG and GLCM are calculated to reveal the intrinsic characteristics of the infrared thermal image to extract feature vectors. Then the IFA is utilized to optimize the parameters of SVM so as to construct an optimal classifier for fault diagnosis. Finally, the proposed fault diagnosis method is fully evaluated by experimentation and the results verify its feasibility and superiority.
40
Babu, D. Ravindra, R. C. Verma, Navneet Kumar Agrawal, and Isha Suwalk. "Comparison of Adapted and Improved Feature Extraction Techniques of Different Potatoes Types using Image Processing." International Journal of Environment, Agriculture and Biotechnology 9 (2024): 161–70. http://dx.doi.org/10.22161/ijeab.94.22.
Full textAbstract:
The characteristics of crack, rotten, sprout, skin peel and good potatoes non destructively with gray level co-occurrence matrix properties (GLCMP), radon, gabor, local binary patterns (LBP) and histogram of oriented gradients (HOG) with default parameters and values i.e. adapted method were compared with improved method. Gabor feature length (16) of improved method was lower compared to adapted method and improved method and it requires less time to plot gabor magnitude and spatial kernels for all potato classes. Radon feature row vector size is same for both adapted and improved methods for all potato classes but differ in column vector size. At theta value of 90° (improved method), the time taken to plot radon transforms is lower compared to adapted method (using theta value 180°). Gray level co-occurrence matrix properties (GLCMP) such as contrast, correlation, energy and homogeneity values were compared to both adapted and improved methods for all potato types. Contrast values found lower in adapted method for all potato classes compared to improved method. But remaining three properties found highest in adapted method for all potato classes compared to improved method. The default values used in adapted method of HOG feature vector length (26140) is higher compared to improved method (1330) for all types of potato images. For crack and rotten potato images, an improved method required higher time to plot visualization than adapted method, while for sprout, good and skin peel images, adapted method has more visualization time. The LBP feature length in improved method was found higher (185) compared to adapted method (59) for all potato classes. The mean time to plot squared errors in adapted and improved methods for crack images were found to be 0.6378 s and 0.6305 s respectively, for rotten images 0.2098 s and 0.2622 s, for sprout images 0.1911 s and 0.2209 s, for skin peel images 0.2197 and 0.2197 s, for good images 0.2672 and 0.2565 s.
41
Priyadharshini, P., and B. S. E. Zoraida. "Hybrid Semantic Feature Descriptor and Fuzzy C-Means Clustering for Lung Cancer Detection and Classification." Journal of Computational and Theoretical Nanoscience 18, no. 4 (2021): 1263–69. http://dx.doi.org/10.1166/jctn.2021.9391.
Full textAbstract:
Lung cancer (LC) will decrease the yield, which will have a negative impact on the economy. Therefore, primary and accurate the attack finding is a priority for the agro-dependent state. In several modern technologies for early detection of LC, image processing has become a one of the essential tool so that it cannot only early to find the disease accurately, but also successfully measure it. Various approaches have been developed to detect LC based on background modelling. Most of them focus on temporal information but partially or completely ignore spatial information, making it sensitive to noise. In order to overcome these issues an improved hybrid semantic feature descriptor technique is introduced based on Gray-Level Co-Occurrence Matrix (GLCM), Local Binary Pattern (LBP) and histogram of oriented gradients (HOG) feature extraction algorithms. And also to improve the LC segmentation problems a fuzzy c-means clustering algorithm (FCM) is used. Experiments and comparisons on publically available LIDC-IBRI dataset. To evaluate the proposed feature extraction performance three different classifiers are analysed such as artificial neural networks (ANN), recursive neural network and recurrent neural networks (RNNs).
42
Hao, Qian, Xin Guo, and Feng Yang. "Fast Recognition Method for Multiple Apple Targets in Complex Occlusion Environment Based on Improved YOLOv5." Journal of Sensors 2023 (February 6, 2023): 1–13. http://dx.doi.org/10.1155/2023/3609541.
Full textAbstract:
The mechanization and intelligentization of the production process are the main trends in research and development of agricultural products. The realization of an unmanned and automated picking process is also one of the main research hotspots in China’s agricultural product engineering technology field in recent years. The development of automated apple-picking robot is directly related to imaging research, and its key technology is to use algorithms to realize apple identification and positioning. Aiming at the problem of false detection and missed detection of densely occluded targets and small targets by apple picking robots under different lighting conditions, two different apple recognition algorithms are selected based on the apple shape features to study the traditional machine learning algorithm: histogram of oriented gradients + support vector machine (HOG + SVM) and a fast recognition method for multiple apple targets in a complex occlusion environment based on improved You-Only-Look-Once-v5 (YOLOv5). The first is the improvement of the CSP structure in the network. Using parameter reconstruction, the convolutional layer (Conv) and the batch normalization (BN) layer in the CBL (Conv + BN + Leaky_relu activation function) module are fused into a batch-normalized convolutional layer Conv_B. Subsequently, the CA (coordinate attention) mechanism module is embedded into different network layers in the improved designed backbone network to enhance the expressive ability of the features in the backbone network to better extract the features of different apple targets. Finally, for some targets with overlapping occlusions, the loss function is fine-tuned to improve the model’s ability to recognize occluded targets. By comparing the recognition effects of HOG + SVM, Faster RCNN, YOLOv6, and baseline YOLOv5 on the test set under complex occlusion scenarios, the F 1 value of this method was increased by 13.47%, 6.01%, 1.26%, and 3.63%, respectively, and the F 1 value of this method was increased by 19.36%, 13.07%, 1.61%, and 4.27%, respectively, under different illumination angles. The average image recognition time was 0.27 s faster than that of HOG + SVM, 0.229 s faster than that of Faster RCNN, and 0.006 s faster than that of YOLOv6. The method is expected to provide a theoretical basis for apple-picking robots to choose a pertinent image recognition algorithm during operation.
43
Zhou, Yang, Wenzhu Yang, and Yuan Shen. "Scale-Adaptive KCF Mixed with Deep Feature for Pedestrian Tracking." Electronics 10, no. 5 (2021): 536. http://dx.doi.org/10.3390/electronics10050536.
Full textAbstract:
Pedestrian tracking is an important research content in the field of computer vision. Tracking is achieved by predicting the position of a specific pedestrian in each frame of a video. Pedestrian tracking methods include neural network-based methods and traditional template matching-based methods, such as the SiamRPN (Siamese region proposal network), the DASiamRPN (distractor-aware SiamRPN), and the KCF (kernel correlation filter). The KCF algorithm has no scale-adaptive capability and cannot effectively solve the occlusion problem, and because of many defects of the HOG (histogram of oriented gradient) feature that the KCF uses, the tracking target is easy to lose. For those defects of the KCF algorithm, an improved KCF model, the SKCFMDF (scale-adaptive KCF mixed with deep feature) algorithm was designed. By introducing deep features extracted by a newly designed neural network and by introducing the YOLOv3 (you only look once version 3) object detection algorithm, which was also improved for more accurate detection, the model was able to achieve scale adaptation and to effectively solve the problem of occlusion and defects of the HOG feature. Compared with the original KCF, the success rate of pedestrian tracking under complex conditions was increased by 36%. Compared with the mainstream SiamRPN and DASiamRPN models, it was still able to achieve a small improvement.
44
Theresa, W. Gracy, S. Santhana Prabha, D. Thilagavathy, and S. Pournima. "Analysis of the Efficacy of Real-Time Hand Gesture Detection with Hog and Haar-Like Features Using SVM Classification." International Journal on Recent and Innovation Trends in Computing and Communication 10, no. 2s (2022): 199–207. http://dx.doi.org/10.17762/ijritcc.v10i2s.5929.
Full textAbstract:
The field of hand gesture recognition has recently reached new heights thanks to its widespread use in domains like remote sensing, robotic control, and smart home appliances, among others. Despite this, identifying gestures is difficult because of the intransigent features of the human hand, which make the codes used to decode them illegible and impossible to compare. Differentiating regional patterns is the job of pattern recognition. Pattern recognition is at the heart of sign language. People who are deaf or mute may understand the spoken language of the rest of the world by learning sign language. Any part of the body may be used to create signs in sign language. The suggested system employs a gesture recognition system trained on Indian sign language. The methods of preprocessing, hand segmentation, feature extraction, gesture identification, and classification of hand gestures are discussed in this work as they pertain to hand gesture sign language. A hybrid approach is used to extract the features, which combines the usage of Haar-like features with the application of Histogram of Oriented Gradients (HOG).The SVM classifier is then fed the characteristics it has extracted from the pictures in order to make an accurate classification. A false rejection error rate of 8% is achieved while the accuracy of hand gesture detection is improved by 93.5%.
45
David, Leo Gertrude, Raj Kumar Patra, Przemysław Falkowski-Gilski, Parameshachari Bidare Divakarachari, and Lourdusamy Jegan Antony Marcilin. "Tool Wear Monitoring Using Improved Dragonfly Optimization Algorithm and Deep Belief Network." Applied Sciences 12, no. 16 (2022): 8130. http://dx.doi.org/10.3390/app12168130.
Full textAbstract:
In recent decades, tool wear monitoring has played a crucial role in the improvement of industrial production quality and efficiency. In the machining process, it is important to predict both tool cost and life, and to reduce the equipment downtime. The conventional methods need enormous quantities of human resources and expert skills to achieve precise tool wear information. To automatically identify the tool wear types, deep learning models are extensively used in the existing studies. In this manuscript, a new model is proposed for the effective classification of both serviceable and worn cutting edges. Initially, a dataset is chosen for experimental analysis that includes 254 images of edge profile cutting heads; then, circular Hough transform, canny edge detector, and standard Hough transform are used to segment 577 cutting edge images, where 276 images are disposable and 301 are functional. Furthermore, feature extraction is carried out on the segmented images utilizing Local Binary Pattern (LBPs) and Speeded up Robust Features (SURF), Harris Corner Detection (HCD), Histogram of Oriented Gradients (HOG), and Grey-Level Co-occurrence Matrix (GLCM) feature descriptors for extracting the texture feature vectors. Next, the dimension of the extracted features is reduced by an Improved Dragonfly Optimization Algorithm (IDOA) that lowers the computational complexity and running time of the Deep Belief Network (DBN), while classifying the serviceable and worn cutting edges. The experimental evaluations showed that the IDOA-DBN model attained 98.83% accuracy on the patch configuration of full edge division, which is superior to the existing deep learning models.
46
Yousef, Amr, Jeff Flora, and Khan Iftekharuddin. "Monocular Camera Viewpoint-Invariant Vehicular Traffic Segmentation and Classification Utilizing Small Datasets." Sensors 22, no. 21 (2022): 8121. http://dx.doi.org/10.3390/s22218121.
Full textAbstract:
The work presented here develops a computer vision framework that is view angle independent for vehicle segmentation and classification from roadway traffic systems installed by the Virginia Department of Transportation (VDOT). An automated technique for extracting a region of interest is discussed to speed up the processing. The VDOT traffic videos are analyzed for vehicle segmentation using an improved robust low-rank matrix decomposition technique. It presents a new and effective thresholding method that improves segmentation accuracy and simultaneously speeds up the segmentation processing. Size and shape physical descriptors from morphological properties and textural features from the Histogram of Oriented Gradients (HOG) are extracted from the segmented traffic. Furthermore, a multi-class support vector machine classifier is employed to categorize different traffic vehicle types, including passenger cars, passenger trucks, motorcycles, buses, and small and large utility trucks. It handles multiple vehicle detections through an iterative k-means clustering over-segmentation process. The proposed algorithm reduced the processed data by an average of 40%. Compared to recent techniques, it showed an average improvement of 15% in segmentation accuracy, and it is 55% faster than the compared segmentation techniques on average. Moreover, a comparative analysis of 23 different deep learning architectures is presented. The resulting algorithm outperformed the compared deep learning algorithms for the quality of vehicle classification accuracy. Furthermore, the timing analysis showed that it could operate in real-time scenarios.
47
Huang, Xu, Yongjun Zhang, and Zhaoxi Yue. "IMAGE-GUIDED NON-LOCAL DENSE MATCHING WITH THREE-STEPS OPTIMIZATION." ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences III-3 (June 3, 2016): 67–74. http://dx.doi.org/10.5194/isprsannals-iii-3-67-2016.
Full textAbstract:
This paper introduces a new image-guided non-local dense matching algorithm that focuses on how to solve the following problems: 1) mitigating the influence of vertical parallax to the cost computation in stereo pairs; 2) guaranteeing the performance of dense matching in homogeneous intensity regions with significant disparity changes; 3) limiting the inaccurate cost propagated from depth discontinuity regions; 4) guaranteeing that the path between two pixels in the same region is connected; and 5) defining the cost propagation function between the reliable pixel and the unreliable pixel during disparity interpolation. This paper combines the Census histogram and an improved histogram of oriented gradient (HOG) feature together as the cost metrics, which are then aggregated based on a new iterative non-local matching method and the semi-global matching method. Finally, new rules of cost propagation between the valid pixels and the invalid pixels are defined to improve the disparity interpolation results. The results of our experiments using the benchmarks and the Toronto aerial images from the International Society for Photogrammetry and Remote Sensing (ISPRS) show that the proposed new method can outperform most of the current state-of-the-art stereo dense matching methods.
48
Huang, Xu, Yongjun Zhang, and Zhaoxi Yue. "IMAGE-GUIDED NON-LOCAL DENSE MATCHING WITH THREE-STEPS OPTIMIZATION." ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences III-3 (June 3, 2016): 67–74. http://dx.doi.org/10.5194/isprs-annals-iii-3-67-2016.
Full textAbstract:
This paper introduces a new image-guided non-local dense matching algorithm that focuses on how to solve the following problems: 1) mitigating the influence of vertical parallax to the cost computation in stereo pairs; 2) guaranteeing the performance of dense matching in homogeneous intensity regions with significant disparity changes; 3) limiting the inaccurate cost propagated from depth discontinuity regions; 4) guaranteeing that the path between two pixels in the same region is connected; and 5) defining the cost propagation function between the reliable pixel and the unreliable pixel during disparity interpolation. This paper combines the Census histogram and an improved histogram of oriented gradient (HOG) feature together as the cost metrics, which are then aggregated based on a new iterative non-local matching method and the semi-global matching method. Finally, new rules of cost propagation between the valid pixels and the invalid pixels are defined to improve the disparity interpolation results. The results of our experiments using the benchmarks and the Toronto aerial images from the International Society for Photogrammetry and Remote Sensing (ISPRS) show that the proposed new method can outperform most of the current state-of-the-art stereo dense matching methods.
49
Liu, Guocheng, Caixia Zhang, Qingyang Xu, et al. "I3D-Shufflenet Based Human Action Recognition." Algorithms 13, no. 11 (2020): 301. http://dx.doi.org/10.3390/a13110301.
Full textAbstract:
In view of difficulty in application of optical flow based human action recognition due to large amount of calculation, a human action recognition algorithm I3D-shufflenet model is proposed combining the advantages of I3D neural network and lightweight model shufflenet. The 5 × 5 convolution kernel of I3D is replaced by a double 3 × 3 convolution kernels, which reduces the amount of calculations. The shuffle layer is adopted to achieve feature exchange. The recognition and classification of human action is performed based on trained I3D-shufflenet model. The experimental results show that the shuffle layer improves the composition of features in each channel which can promote the utilization of useful information. The Histogram of Oriented Gradients (HOG) spatial-temporal features of the object are extracted for training, which can significantly improve the ability of human action expression and reduce the calculation of feature extraction. The I3D-shufflenet is testified on the UCF101 dataset, and compared with other models. The final result shows that the I3D-shufflenet has higher accuracy than the original I3D with an accuracy of 96.4%.
50
Zhen, Xinxin, Shumin Fei, Yinmin Wang, and Wei Du. "A Visual Object Tracking Algorithm Based on Improved TLD." Algorithms 13, no. 1 (2020): 15. http://dx.doi.org/10.3390/a13010015.
Full textAbstract:
Visual object tracking is an important research topic in the field of computer vision. Tracking–learning–detection (TLD) decomposes the tracking problem into three modules—tracking, learning, and detection—which provides effective ideas for solving the tracking problem. In order to improve the tracking performance of the TLD tracker, three improvements are proposed in this paper. The built-in tracking module is replaced with a kernelized correlation filter (KCF) algorithm based on the histogram of oriented gradient (HOG) descriptor in the tracking module. Failure detection is added for the response of KCF to identify whether KCF loses the target. A more specific detection area of the detection module is obtained through the estimated location provided by the tracking module. With the above operations, the scanning area of object detection is reduced, and a full frame search is required in the detection module if objects fails to be tracked in the tracking module. Comparative experiments were conducted on the object tracking benchmark (OTB) and the results showed that the tracking speed and accuracy was improved. Further, the TLD tracker performed better in different challenging scenarios with the proposed method, such as motion blur, occlusion, and environmental changes. Moreover, the improved TLD achieved outstanding tracking performance compared with common tracking algorithms.