A new Local-Main-Gradient-Orientation HOG and contour differences based algorithm for object classification

We present a Histogram of Oriented Gradient (HoG) based two-directional Dynamic Time Warping (DTW) matching method for handwritten word spotting. Firstly, we extract HoG descriptors from each cell in the normalized images. Then we connect the HoG descriptors in the same column and get a sequence of feature vectors. We do the same operation for the HoG descriptors in the same row. We then apply the two-directional DTW method to calculate the distance between the feature vectors sequences extracted from the query word and the candidate one. The experimental results show that the two-directional DTW is more robust to word deformation than the traditional DTW. And the local features such as HoG, LBP and SIFT combined with the two-directional DTW method outperform the method using the local feature descriptors directly. The HoG based two-directional DTW get the highest mean average precision on both the George Washington dataset and the CASIA-HWDB 2.1 dataset.

Maximum Curvature Method (MCM) is one of the promising methods for finger vein verification. MCM scans the curvature of the vein image profiles within a finger for feature extraction. However, the quality of the image can be poor due to variations in illumination and sensor conditions. Furthermore, traditional MCM matching of the vein pattern requires extensive processing time. To address these limitations, we propose an integrated Enhanced Maximum Curvature (EMC) method with Histogram of Oriented Gradient (HOG) descriptor for finger vein verification. Unlike MCM, EMC incorporates an enhancement mechanism to extract small vein delineation that is hardly visible in the extracted vein patterns. Next, HOG is applied instead of image binarization to convert a two-dimensional vein image into a one-dimensional feature vector for efficient matching. The HOG descriptor is able to characterize the local spatial representation of a finger vein by capturing the gradient information effectively. The proposed method is evaluated based on two datasets namely the PKU Finger Vein Database (V4) and SDUMLA-HMT finger vein database. Experiments show promising verification results with equal error rates as low as 0.33 % for DB1 and 0.14 % for DB2 respectively, when EMC+HOG+SVM is applied.

Principal curvatures based rotation invariant algorithms for efficient texture classification

Human detection and tracking is a task common to many applications, such as video surveillance and security, intelligent vehicles, safety driving, public security, etc. Histogram of oriented gradient (HOG) gives an accurate description of the contour of human body. Based on HOG and support vector machine (SVM) theory, a classifier for pedestrian is obtained. The classifier is then used to find the potential human candidate in the video frame. By calculating the similarity between particle candidates and the target model using Bhattacharyya Coefficient, a tracking algorithm using particle filter is designed and implemented. Experimental results show that the proposed algorithm out-performs Kalman filter based tracking in almost all situations, especially when partial occlusion of object is present.

Recently, pedestrian detection system has become an important issue to improve the road safety through its integration in several Advanced Driver Assistance Systems (ADAS). According to the literature, the use of the Histogram of Oriented Gradients (HOG) descriptor has been very efficient and robust in the development of such systems. However, the intensive calculation steps of this descriptor make its implementation an issue to be address in order to meet real-time requirement. In this paper, an efficient hardware architecture based on an improved HOG version and linear SVM (Support Vector Machine) classifier is emphasized. The proposed architecture has founded on cell-based scanning, some approximations and without any pixelbuffers. The system evaluation was carried out on a Xilinx Zynq platform. Experimental results showed that our approach can achieve an efficient pedestrian detection for full HD (High-Definition) video with a reduced hardware resource and power consumption.

The problem of detecting objects in images is solved by training the classifier by the descriptors constructed based on the local Radon transform of the gradient field of the image. The space of the Radon transform is considered as the Hough space accumulator in which projections are constructed. The set of local projections forms a descriptor of the region related to the object that is a generalization of the known histogram of oriented gradients (HOG) descriptor. The issues of the effect of the approximation of the Radon transform contribution function, the form of local normalization, and the number of directions in the projection histograms on the results of detecting pedestrians are investigated. The results produced by the proposed descriptor are compared with the results obtained using the HOG descriptor and convolutional neural networks (CNN) based on the ResNext and MobileNet architectures on the INRIA and CityScapes databases.

Due to the advancements in digital technologies and social networking, image collections are growing exponentially. The important aim in content-based image retrieval (CBIR) is to reduce the semantic gap issue that improves the performance of image retrieval. In this paper, the objective is achieved by introducing effective visual words fusion technique based on speeded-up robust features (SURF) and histograms of oriented gradients (HOG) feature descriptors. HOG is used to extract global features, whereas SURF is used for the extraction of local features. Global features are preferred for large-scale image retrieval, whereas local features perform better on those systems that support semantic queries with close visual appearance. Moreover, SURF is scale and rotation-invariant as compared to HOG descriptor and it works better for low illumination. On the contrary, HOG performs better for scene-recognition- or activity-recognition-based applications. In the proposed technique, visual words fusion of SURF and HOG feature descriptors is carried which performed better than features fusion of SURF and HOG feature descriptors as well as state-of-the-art CBIR techniques. The proposed technique based on visual words fusion gives classification accuracy of 98.40% using support vector machine while image retrieval accuracy of 80.61%. Qualitative and quantitative analyses performed on four standard image collections namely, Corel-1000, Corel-1500, Corel-5000, and Caltech-256 demonstrate the effectiveness of the proposed technique based on visual words fusion of SURF and HOG feature descriptors.

Cars can appear at any orientations in satellite images, but the widely used traditional histogram of oriented gradient (HOG) features is not rotation-invariant. Recently, a rotation-invariant HOG descriptor using Fourier analysis in polar coordinators has been proposed and has shown good performance; however, it is time and memory consuming. In this study, the authors improve this method to present an efficient rotation-invariant HOG descriptor for car detection in satellite images. The authors first convert spatial convolutions to multiplications in the frequency domain based on fast Fourier transform to speed up the descriptor computation. Then, they employ a backward search feature selection method based on support vector machine to reduce the descriptor dimensionality. This allows them to build the proposed efficient rotation-invariant HOG descriptor at low time and memory cost. The authors demonstrate that their method is more efficient and yields better detection performance in a public dataset for car detection task in satellite images.

In the modern era, cancer is a major public health concern. Breast cancer is one of the leading causes of death among women. Breast cancer is becoming the top cause of death in women worldwide. Early identification of breast cancer allows patients to receive proper treatment, improving their chances of survival. The proposed Generative Adversarial Networks (GAN) approach is designed to aid in the detection and diagnosis of breast cancer. GANs are deep learning algorithms that generate new data instances that mimic the training data. GAN is made up of two parts: a generator that learns to generate false data and a discriminator that learns from this false data. Furthermore, the histogram of oriented gradients (HOG) is utilized as a feature descriptor in image processing and other computer vision techniques. Gradient orientation in the detection window and region of interest is determined by the histogram of oriented gradients descriptor approach. Using an image dataset and deep learning techniques, the proposed research (GAN-HOG) aims to improve the efficiency and performance of breast cancer diagnosis. The deep learning method is used here to analyze image data by segmenting and classifying the input photographs from the dataset. Unlike many existing nonlinear classification models, the proposed method employs a conditional distribution for the outputs. The proposed model GAN-HOG had an accuracy of 98.435%, a ResNet50 accuracy of 87.826%, a DCNN accuracy of 92.547%, a VGG16 accuracy of 89.453%, and an SVM accuracy of 95.546%.

The aim of our work is to investigate the use of two powerful feature descriptor known as Zernike moments and histogram of oriented gradient (HOG) for facial images extracted from a video sequence uttered ten times by four speakers where MLP neural network classifier is used to identify the correct speaker. We've demonstrated good recognition rate obtained for both Zernike moments and HOG descriptors.

Scientists have attempted to enhance face recognition accuracy by using 3D images to solve pose variability, lighting issues, and occlusion; but the applicability of these approaches is insufficient in realistic applications due to the slowness and high cost of 3D sensors. In this paper, we developed a face recognition process for low-cost and low-quality Microsoft Kinect sensor based on the Histogram of Oriented Gradient (HOG) descriptor. After locating the nose tip, the face is extracted and filtered to reduce the noise, the feature vectors are extracted by first computing the shape index map and then applying the HOG descriptor. For identification, the Collaborative Representation Classifier (CRC) is used. We compare our approach results with previous ones obtained on the publicly available CurtinFaces database, achieving rank one recognition rates of 99.87% and 82.53% when testing against expression and pose variations respectively.

Employing histogram of oriented gradient to enhance concrete crack detection performance with classification algorithm and Bayesian optimization

Histograms of oriented gradients (HOG) is the most successful feature descriptor in pedestrian detection; however, it is limited because of only considering the gradient. It has a certain false-positive rate on some examples, which have a lot of parallel vertical components (looks like a leg or a body) due to lacking of texture feature. This paper proposes a method to combine a cell-structured HOG feature and adaptive local binary pattern feature to solve the problem that HOG is vulnerable to the interference of vertical background gradient information in pedestrian detection. In addition, we use a fast method to utilize sub-cell-based interpolation to efficiently compute HOG feature for each block. Training the combination feature to get a discriminative model by bootstrapped linear support vector machine. Experimental results on the INRIA dataset have demonstrated the effectiveness and efficiency of the proposed method.

Forthcoming surveys such as the Large Synoptic Survey Telescope (LSST) and Euclid necessitate automatic and efficient identification methods of strong lensing systems. We present a strong lensing identification approach that utilizes a feature extraction method from computer vision, the Histogram of Oriented Gradients (HOG), to capture edge patterns of arcs. We train a supervised classifier model on the HOG of mock strong galaxy–galaxy lens images similar to observations from the Hubble Space Telescope (HST) and LSST. We assess model performance with the area under the curve (AUC) of a Receiver Operating Characteristic (ROC) curve. Models trained on 10,000 lens and non-lens containing images exhibit an AUC of 0.975 for an HST-like sample, 0.625 for one exposure of LSST, and 0.809 for 10 yr mock LSST observations. Performance appears to continually improve with the training set size. Models trained on fewer images perform better in the absence of the lens galaxy light. However, with larger training data sets, information from the lens galaxy actually improves model performance, indicating that HOG captures much of the morphological complexity of the arc-finding problem. We test our classifier on data from the Sloan Lens ACS Survey and find that small-scale image features reduce the efficiency of our trained model. However, these preliminary tests indicate that some parameterizations of HOG can compensate for differences between observed mock data. One example best-case parameterization results in an AUC of 0.6 in the F814 filter image, with other parameterization results equivalent to random performance.

Automatic classification of severe and mild wear in worn surface images using histograms of oriented gradients as descriptor