Speed Limit Traffic Sign Classification Using Multiple Features Matching

As artificial intelligence develops, deep learning algorithms are increasingly being used in the field of dorsal hand vein (DHV) recognition. However, deep learning has high requirements regarding the number of samples, and current DHV datasets have few images. To solve the above problems, we propose a method based on the fusion of ResNet and Histograms of Oriented Gradients (HOG) features, in which the shallow semantic information extracted by primary convolution and HOG features are fed into the residual structure of ResNet for full fusion and, finally, classification. By adding Gaussian noise, the North China University of Technology dataset, the Shandong University of Science and Technology dataset, and the Eastern Mediterranean University dataset are extended and fused to from a fused dataset. Our proposed method is applied to the above datasets, and the experimental results show that our proposed method achieves good recognition rates on each of the datasets. Importantly, we achieved a 93.47% recognition rate on the fused dataset, which was 2.31% and 26.08% higher than using ResNet and HOG alone.

Face recognition is efficiently used in computer vision, pattern recognition, biometric, law enforcement, surveillance, criminal investigations, and missing person detection. However, face recognition is still a challenging task under variant illuminations, pose, expression, occlusion, and background. In this paper, we proposed a cascading of histogram of oriented gradients (HOG) and local binary pattern (LBP) feature extraction method on ORL face dataset, which can improve recognition rates while also addressing pose, scale, expression, and variant illumination issues. The facial recognition network was trained using various classifiers such as with KNN, SVM, and random forest (RF). The results have been shown that the accuracy rate of the combined LBP and HOG feature extraction method is better than individual LBP or HOG features for ORL database face recognition.

The estimation of the number of people in surveillance areas is essential for monitoring crowded scenes. When density of a zone increases to a certain approximated level, people's safety can be endangered. Detection of human is a prerequisite for density estimation, tracking, activity recognition and anomaly detection even in non congested areas. This paper presents a robust hybrid approach for face detection in crowd by combining the skin color segmentation and a Histogram of Oriented Gradients(HOG) with Support Vector Machine(SVM) architecture. Initially, image enhancement is performed to improve the detection rate. An edge preserving pyramidal approach is applied for multiscale representation of an image. Skin color segmentation is done with combination of YCbCr and RGB color model, and HOG features are extracted from the segmented skin region. We trained the SVM classifier by Muct and FEI databases which consist 751 and 2800 face images respectively. The accuracy of this approach is evaluated by testing it on BAO multiple face database and on various manually collected images captured in surveillance areas. Experimental results demonstrate that the supplementary skin color segmentation with HOG is more potent for increasing the detection rate than using HOG features only. The proposed approach achieves 98.02% accuracy which is higher in comparison to Viola Jones and fast face detection method.

Extraction of global face appearance and local interior differences is essential for any face recognition application. This paper presents a novel framework for face recognition by combining two effective descriptors namely, Zernike moments (ZM) and histogram of oriented gradients (HOG). ZMs are global descriptors that are invariant to image rotation, noise and scale. HOGs capture local details and are robust to illumination changes. Fusion of these two descriptors combines the merits of both local and global approaches and is effective against diverse variations present in face images. Further, as the processing time of HOG features is high owing to its large dimensionality, so, the study proposes to improve its performance by selecting only most discriminative HOG features (named discriminative HOG (DHOG)) for performing recognition. Efficacy of the proposed methods (DHOG, [Formula: see text] and [Formula: see text]) is tested on ORL, Yale and FERET databases. DHOG provides an improvement of 3% to 5% over the existing HOG approach. Recognition results achieved by [Formula: see text] and [Formula: see text] are up to 15% and 18% higher respectively than those obtained with these descriptors individually. Performance is also analyzed on LFW face database and compared with recent and state-of-the-art methods.

Due to the inherent characteristics of synthetic aperture radar (SAR) imaging, SAR ship features are not obvious and the category distribution is unbalanced, which makes the task of ship recognition in SAR images quite challenging. To address the above problems, a two-level feature-fusion ship recognition strategy combining the histogram of oriented gradients (HOG) features with the dual-polarized data in the SAR images is proposed. The proposed strategy comprehensively utilizes the features extracted by the HOG operator and the shallow and deep features extracted by the Siamese network in the dual-polarized SAR ship images, which can increase the amount of information for the model learning. First, the Siamese network is used to extract the shallow and deep features from the dual-polarized SAR images, and then the HOG feature of the dual-polarized SAR images is also extracted. Furthermore, the bilinear transformation layer is used for fusing the HOG features from dual-polarized SAR images, and the grouping bilinear pooling process is used for fusing the dual-polarized shallow feature and deep feature extracted by the Siamese network, respectively. Finally, the catenation operation is used for fusing the dual-polarized HOG features and dual-polarized shallow feature and deep feature, respectively, which are used for the recognition of the SAR ship targets. Experimental results tested on the OpenSARShip2.0 dataset demonstrate the correctness and effectiveness of the proposed strategy, which can effectively improve the recognition performance of the ship targets by fusing the different level features of the dual-polarized SAR images.

In order to detect pedestrians in many applications, histogram of oriented gradient (HOG) feature is widely used. Although HOG feature can provide high detection accuracy, fast detection time is hardly achieved due to its computational complexity. In this paper, a new method for pedestrian detection using HOG feature is proposed to achieve both high detection rate and fast detection time. Multi-scale cells and blocks of HOG feature are used to improve detection accuracy, and they are computed by using integral HOG to improve detection speed. In order to further improve detection quality in terms of accuracy and speed, two-stage approach is adopted in the proposed method. Experimental results show that the proposed method improves both detection rate and speed.

Feature extraction plays a pivotal role in pattern recognition and matching. An ideal feature should be invariant to image transformations such as translation, rotation, scaling, etc. In this work, we present a novel rotation-invariant feature, which is based on Histogram of Oriented Gradients (HOG). We compare performance of the proposed approach with the HOG feature on 2D phantom data, as well as 3D medical imaging data. We have used traditional histogram comparison measures such as Bhattacharyya distance and Normalized Correlation Coefficient (NCC) to assess efficacy of the proposed approach under effects of image rotation. In our experiments, the proposed feature performs 40%, 20%, and 28% better than the HOG feature on phantom (2D), Computed Tomography (CT-3D), and Ultrasound (US-3D) data for image matching, and landmark tracking tasks respectively.

Histogram of Oriented Gradients (HOG) features are the underlying representation in automotive computer vision applications such as collision avoidance and lane keeping. In these applications, we have observed that HOG feature computation is often a slow and energy-intensive component of the overall pipeline. In this paper, we focus on reducing both the time taken and the energy used for computing Felzenszwalb HOG features. We achieve our results though a combination of reduced precision, SIMD parallelism, algorithmic changes, and outer-loop parallelism. In particular, we address a bottleneck in histogram accumulation by phrasing the problem as a gather instead of the (traditional) scatter. Additionally, we explore the tradeoffs of using L1 instead of L2 norms to compute gradients, which enables smaller operands and more SIMD parallelism. Overall, we are able to compute multiresolution HOG pyramids at 70fps for 640×480 images on a multicore CPU. This is a 3.6x speedup over the best known HOG implementation and a 29× speedup over the popular voc-release5 HOG code. This is also a 3.6× - 22× reduction in energy per frame compared to previous HOG implementations. Our open-source implementation is available for download.

Histogram of Oriented Gradients (HOG) feature descriptor is very effective to represent objects and is widely used in human and face detection. In this paper, HOG feature descriptor is applied for Content-based Image Retrieval (CBIR). For handling similarity measurement of large amount of database, vocabulary tree is used. Experimental results illustrate the comparative analysis of retrieval system based on HOG feature descriptor and Gabor transform feature descriptor. It is verified that HOG-based retrieval system improves Average Precision (AP) and Average Recall (AR) (56.75% and 38.45%, respectively) from Gabor-transform-based retrieval system (41.20% and 25.41%, respectively). All the experiments are performed on Corel 1000 natural image database.

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.

In this study, normal (n), benign (b), and malign (m) stomach image cells have taken from faculty of Medicine the Fırat University with Light Microscope help. Total number of stomach images are 180 which be 60 n, 60 b, and 60 m. 90 of these 180 stomach images have been used for testing purposes and 90 have used for training purposes. The histograms of oriented gradient (HOG) feature vectors have been obtained for normal, benign, and malign original stomach images. The size of these HOG feature vectors is 46900×180. High-dimensional of these HOG feature vectors is reduced to lower-dimensional with Linear Discriminant Analysis (LDA). These low-dimensional data are 180×180. These low-dimensional data are classified as normal benign and malign by artificial neural network (ANN) classification. Thus, HOG_LDA_ANN method for stomach cancer images have developed. Diagnostic accuracy of classification results with this method has found as 88.9%. According to the other methods, this result has higher accuracy result. And this result has found in a shorter time.

This paper proposed a novel method for face hallucination based on a neighbor embedding technique. Traditional neighbor embedding approaches often offer counterintuitive results because consistency between high resolution images and low resolution images cannot be preserved without taking the intrinsic features of the image patches into account. In order to reinforce the consistency, on the one hand, we exploit the singular-values-unique (SVU) features inspired by singular values decomposition (SVD) successfully applied in image processing. On the other hand, we introduced the Histograms of Oriented Gradients (HOG) features to characterize the local geometric structure of the image patches to alleviate the effects of noise. At last, the learning space is extended to a coupled feature space that combines the SVU and HOG features. Simulation experiments show that this proposed approach could provide competitive results in simulation experiments in subjective and objective quality.

In complex scene, considering traditional object detection methods based on feature points have exposed many problems, such as undetected points, low detected ratio and cannot well process object occlusion and scaling situation, this paper proposes a detection method which based on a deformable part model. The method uses histogram of oriented gradient (HOG) feature as the object description, and the deformable part model includes a global template and several high-resolution templates. And the method uses the support vector machine (SVM) training the object model. In the learning process, after the HOG feature extracted, the method modifies the HOG feature, and then uses the principal component analysis (PCA) method reducing feature dimensions to avoid over-learning, and improve the detection rate in the detection process. The experiment results shows that the method proposed can better process object occlusion or scaled situation, and there’s also an improvement in detection ratio.

Edge is a very important type of feature for human detection and Histogram of Oriented Gradient (HOG) is the most popular method to encode edge information since proposed. Because HOG detects edges based on intensity gradients, it is not invariant with respect to image illumination. In this paper, we propose three new types of features based on local phase: Local Phase based symmetry (LPS), Local Phase based Asymmetry (LPA), and Histogram of Oriented Asymmetry (HOA) for human detection. The LPA and HOA are similar with gradient magnitude and HOG features, but from different perspective. The key idea is the intensity around an edge point in an image is always asymmetry. Thus we can detect edges by measuring the asymmetry of the local structure at every point in the image. This is achieved by analyzing the phase of its constituent frequency components. This asymmetry measurement is invariant with respect to image contrast. After the asymmetry is computed, this value could be distributed to different orientation bins according to gradient orientation. We also measure symmetry around each point which yields LPS. This is useful to detect torso and limbs. These local phase induced features are combined with the classical Aggregated Channel Features (ACF) and are fed into the boosted decision tree (BDT) framework. Experiment shows that the proposed features are complementary to the ACF features and will increase the detection accuracy.

To improve the performance of thyroid standard plane scanning, this paper proposes a classification algorithm for classifying thyroid ultrasound images using texture features. Firstly, the region of interest of ultrasound images is chosen in the preprocessing process step. Secondly, the local binary patterns (LBP) features and the histograms of oriented gradients (HOG) features of the images are extracted. Then the obtained feature vectors are spliced as the input of the support vector machine (SVM) which is used to classify the thyroid standard plane images. In the experiment, there are 4,574 thyroid standard plane images are used in this paper, which are divided into 8 categories, of which 3,655 pictures for training, and 919 pictures for testing. The experimental results show that the classification accuracy is up to 88.58%, which show a fact that the proposed algorithm has a good discriminating ability for the standard eight-category thyroid plane images, which can assist the doctor to diagnose to a certain extent.