HOG Features Research Articles

Privacy-Oriented Successive Approximation Image Position Follower Processing

In this paper, we analyze the location-following processing of the image by successive approximation with the need for directed privacy. To solve the detection problem of moving the human body in the dynamic background, the motion target detection module integrates the two ideas of feature information detection and human body model segmentation detection and combines the deep learning framework to complete the detection of the human body by detecting the feature points of key parts of the human body. The detection of human key points depends on the human pose estimation algorithm, so the research in this paper is based on the bottom-up model in the multiperson pose estimation method; firstly, all the human key points in the image are detected by feature extraction through the convolutional neural network, and then the accurate labelling of human key points is achieved by using the heat map and offset fusion optimization method in the feature point confidence map prediction, and finally, the human body detection results are obtained. In the study of the correlation algorithm, this paper combines the HOG feature extraction of the KCF algorithm and the scale filter of the DSST algorithm to form a fusion correlation filter based on the principle study of the MOSSE correlation filter. The algorithm solves the problems of lack of scale estimation of KCF algorithm and low real-time rate of DSST algorithm and improves the tracking accuracy while ensuring the real-time performance of the algorithm.

Infant Action Database: A Benchmark for Infant Action Recognition in Uncontrolled condition

The main focus of our work is to create a database for action recognition of unattended infants in uncontrolled environment with wide variations in surroundings, lighting, interactions with objects, camera motions, etc., Action recognition of infants is emerging as an important and technically challenging computer vision problem as compared with adult action recognition because of their physical appearance. Most of the previous action recognition techniques have focused on the recognition of action captured under a controlled environment in a standard laboratory setting. In this study a novel database is introduced that can be used as a benchmark for surveillance parenting. This database involves nine normal and nine abnormal actions classes which consist of actions and movements of infants occurring in fairly uncontrolled conditions. This database consists of realistic user-uploaded videos which are recorded in the clustered background and different camera motion. After the collection of all videos, they are manually trimmed to form a database. To further evaluate the performance of the database, HOG features were extracted from database set and trained by different Machine Learning classifiers like Multi-class Naive Bayes, Support Vector Machine, Ensemble classifier, Discriminant analysis and Decision tree classifiers. This experimentation shows that the database is complex and robust that can serve as a base for testing action recognition algorithms.

Multi-feature fusion tracking algorithm based on generative compression network

In order to solve the problem of inaccurate positioning in the process of target tracking due to illumination, scale change and occlusion, a correlation filtering tracking algorithm based on generate compression network is proposed. Firstly, the encoder is used to compress the high-dimensional depth features extracted from VGG16 network, and the soft quantizer reduces floating-point operation so that improves the operation speed. Secondly, the discriminator of generative adversarial network guides the encoder and generator to better compress and recover the original depth features by generating a discriminator against the network, so as to enhance the ability of the encoder to extract the key features of the target, then, the compressed depth features, gray features and hog features are combined to improve the ability of target representation. Thirdly, the correlation filter and PCA feature dimensionality reduction are used to complete the target precise location and discriminant scale estimation. The experimental results show that the tracking accuracy of the proposed algorithm is 87.1%, and the tracking rate is up to 70fps.

Vehicle Detection using Haar and HOG Feature Extraction Algorithms and SVM with Speed Estimation

Vehicle Detection using Haar and HOG Feature Extraction Algorithms and SVM with Speed Estimation

Recognition of Automated Hand-written Digits on Document Images Making Use of Machine Learning Techniques

The purpose of this study is to create an automated framework that can recognize similar handwritten digit strings. For starting the experiment, the digits were separated into different numbers. The process of defining handwritten digit strings is then concluded by recognizing each digit recognition module's segmented digit. This research utilizes various machine learning techniques to produce a strong performance on the digit string recognition challenge, including SVM, ANN, and CNN architectures. These approaches use SVM, ANN, and CNN models of HOG feature vectors to train images of digit strings. Deep learning methods organize the pictures by moving a fixed-size monitor over them while categorizing each sub-image as a digit pass or fail. Following complete segmentation, complete recognition of handwritten digits is accomplished. To assess the methods' results, data must be used for machine learning training. Following that, the digit data is evaluated using the desired machine learning methodology. The Experiment findings indicate that SVM and ANN also have disadvantages in precision and efficiency in text picture recognition. Thus, the other process, CNN, performs better and is more accurate. This paper focuses on developing an effective system for automatically recognizing handwritten digits. This research would examine the adaptation of emerging machine learning and deep learning approaches to various datasets, like SVM, ANN, and CNN. The test results undeniably demonstrate that the CNN approach is significantly more effective than the ANN and SVM approaches, ranking 71% higher. The suggested architecture is composed of three major components: image pre-processing, attribute extraction, and classification. The purpose of this study is to enhance the precision of handwritten digit recognition significantly. As will be demonstrated, pre-processing and function extraction are significant elements of this study to obtain maximum consistency.

Recognition of Automated Hand-written Digits on Document Images Making Use of Machine Learning Techniques

The purpose of this study is to create an automated framework that can recognize similar handwritten digit strings. For starting the experiment, the digits were separated into different numbers. The process of defining handwritten digit strings is then concluded by recognizing each digit recognition module's segmented digit. This research utilizes various machine learning techniques to produce a strong performance on the digit string recognition challenge, including SVM, ANN, and CNN architectures. These approaches use SVM, ANN, and CNN models of HOG feature vectors to train images of digit strings. Deep learning methods organize the pictures by moving a fixed-size monitor over them while categorizing each sub-image as a digit pass or fail. Following complete segmentation, complete recognition of handwritten digits is accomplished. To assess the methods' results, data must be used for machine learning training. Following that, the digit data is evaluated using the desired machine learning methodology. The Experiment findings indicate that SVM and ANN also have disadvantages in precision and efficiency in text picture recognition. Thus, the other process, CNN, performs better and is more accurate. This paper focuses on developing an effective system for automatically recognizing handwritten digits. This research would examine the adaptation of emerging machine learning and deep learning approaches to various datasets, like SVM, ANN, and CNN. The test results undeniably demonstrate that the CNN approach is significantly more effective than the ANN and SVM approaches, ranking 71% higher. The suggested architecture is composed of three major components: image pre-processing, attribute extraction, and classification. The purpose of this study is to enhance the precision of handwritten digit recognition significantly. As will be demonstrated, pre-processing and function extraction are significant elements of this study to obtain maximum consistency.

Behavioral Biometric Data Analysis for Gender Classification Using Feature Fusion and Machine Learning.

Biometric security applications have been employed for providing a higher security in several access control systems during the past few years. The handwritten signature is the most widely accepted behavioral biometric trait for authenticating the documents like letters, contracts, wills, MOU’s, etc. for validation in day to day life. In this paper, a novel algorithm to detect gender of individuals based on the image of their handwritten signatures is proposed. The proposed work is based on the fusion of textural and statistical features extracted from the signature images. The LBP and HOG features represent the texture. The writer’s gender classification is carried out using machine learning techniques. The proposed technique is evaluated on own dataset of 4,790 signatures and realized an encouraging accuracy of 96.17, 98.72 and 100% for k-NN, decision tree and Support Vector Machine classifiers, respectively. The proposed method is expected to be useful in design of efficient computer vision tools for authentication and forensic investigation of documents with handwritten signatures.

Approach on Recognizing Uncovered Earth Region from Aerial Images Based on Multi-feature Fusion

It is one of the main hidden dangers of power transmission lines accidents if there is the uncovered earth under or near power transmission lines. It can give the important early warning message to prevent the accidents through recognizing the uncovered earth region from aerial images of Unmanned Aerial Vehicle (UAV) power transmission lines inspection. Due to the low recognizing precision of Mask RCNN CNN (Mask Convolution Neural Network), this paper proposed an approach to recognize the uncovered earth region from aerial images of UAV by image feature fusion. The HOG and LBP features of aerial images were extracted and their dimension were reduced. Then these two features were fused by different weights. The experiments show that, (1) the average precision of recognizing the uncovered earth region can be above 80%, which is the lowest requirement to use; (2) the weights of two features should make the orders of magnitude of the two features as equal as possible. The approach is application for the first image filtering by the UAV airborne platform because it not only has enough good recognizing precision but also is very rapid, which provides a novel way for objective recognition from UAV aerial images.

An ameliorated deep dense convolutional neural network for accurate recognition of casting defects in X-ray images

Recognizing defects in X-ray images plays an important role in the detection of internal defects in titanium alloy castings. However, the existing manual defects recognition methods have common drawbacks such as unstable artificial recognition, misrecognition, huge workload, and low efficiency of recognition. To make up for the shortcomings, an ameliorated deep dense convolutional neural network (BX-Net) was presented to accurately recognize casting defects in X-ray images and effectively extract highly discriminative features of different categories. DenseNet121 was used as the backbone of BX-Net and the feature extracted by DenseNet121 was fully shared by the two inputs of a bilinear pooling layer. Transfer learning was applied to reduce the demand for data and hyperparameters’ tuning. The backbone of BX-Net was firstly trained on the ImageNet and then all layers of BX-Net was fine-tuned on nine-hundred X-ray images of TiAl aero casting components. Other six deep convolutional neural networks (DenseNet121, EfficientNetB4, EfficientNetB7, ResNet50, VGG16 and Xception) were also trained to be compared with the presented BX-Net. Two Support Vector Machines were trained on the LBP features data set and HOG features data set of nine-hundred X-ray images of TiAl aero casting components respectively Experiments comparing BX-Net with other six deep learning models and two machine learning models on one hundred X-ray images (test set) of TiAl aero casting components were carried out. The comparison results show that BX-Net has the least parameters except for the Densenet121. The recall and accuracy of BX-Net were 99% and 99% respectively. In addition, the comparison results also show that BX-Net was the only model that learned discriminative feature representation of the casting X-ray image data set. The BX-Net proposed in this paper is expected to overcome the shortcomings of manual defects recognition.

A hybrid fusion framework to multi-modal bio metric identification

In the recent decade, comprehensive research efforts have been carried out as the promising modality of bio metrics on humans’ physical features for person recognition. Despite this, the main issue encountered in identifying individuals is obtaining rich representation for multi-modal data that is invariant to diverse physical traits. The shortcomings of uni-modal bio metric systems can be tackled by combining derived knowledge from several modalities of bio metric systems embedded with several physical characteristics like Ear, Face, Iris, and Gait. This paper proposes a novel multi-modal bio metric identification framework based on a hybrid multi-phase feature fusion to render compact knowledge from multiple model traits. We employed transfer learning through several pertained networks such as Resnet101, Resnet-Inceptionv2, Densenet201, AlexNet, and Inceptionv2 to fuse with handcrafted feature vectors extracted via Hog feature descriptor. The fusion is performed using Discriminant Correlation Analysis (DCA) and Canonical Correlation Analysis (CCA) at each single and hybrid phase. Three state of the art bio metric databases, namely Face, Gait, and Ear, was utilized to evaluate the proposed framework. The proposed framework based on multi-phase hybrid fusion achieved up to 96.6% of identification accuracy using multi traits. Experimental results confirm the superior results over other recent multi-modal bio metric variants.

Car Surveillance Video Summarization Based On Car Plate Detection

Today, video is a common medium for sharing information. Navigating the internet to download a certain form of video, it takes a long time, a lot of bandwidth, and a lot of disk space. Since sending video over the internet is too costly, therefore video summarization has become a critical technology. Monitoring vehicles of people from a security and traffic perspective is a major issue. This monitoring depends on the identification of the license plate of vehicles. The proposed system includes training and testing stages. Training stage comprises: video preprocessing, Viola-Jones training, and Support Vector Machine (SVM) optimization. Testing stage contains: test video preprocessing, car plate (detection, cropping, resizing, and grouping detecting test car plate, feature extraction using HOG feature. The total time of local recorded videos is (19.5 minutes), (15.5 minutes) for training, and (4 minutes) for testing. This means, (79.5%) for training and (20.5%) for testing. The proposed video summarization has got maximum accuracy of (86%) by using Viola-Jones and SVM by reducing the number of original video frames from (7077) frames to (1200) frames. The accuracy of the Viola-Jones object detection process for training 700 images is (97%). The accuracy of the SVM classifier is (99.6%).

A Computer Vision System for Monitoring Disconnect Switches in Distribution Substations

Knowing the state of the disconnect switches in a power distribution substation is important, since incorrect operation may lead to problems such as accidents, outages, and damaged equipment. Although human errors when reporting switch positions are rare, they can have a large impact when they occur, making automatic monitoring an attractive proposition, especially in substations without permanent staff. In this paper, we describe a non-intrusive computer vision system for monitoring the state of disconnect switches in distribution substations. The system employs regular surveillance cameras, which can also be used for other purposes, leading to lower cost and simpler installation and maintenance compared to individual per-switch sensors. Several challenges were addressed: cluttered backgrounds, occlusions, variations in lighting, weather and switch aspect, and the fact that it is often not possible to maneuver the switches during installation. We addressed these challenges by combining data provided by a human operator during installation with multiple machine learning models, relying on techniques such as SVMs for classifying SIFT or HOG features, and deep learning. By combining multiple outputs, the system achieved a 99.7365% success rate in experiments performed at a real substation over several days.

Ecuadorian regulatory traffic sign detection by using HOG features and ELM classifier

This article presents an algorithm for Ecuadorian regulatory traffic signs detection, under extreme lighting conditions during the day. The method is composed of the following modules, i) video stabilization to reduce vertical oscilation, ii) a method to for obtaining regions of interest (ROIs) based on color information and geometric restrictions, iii) a two-stage multi classification algorithm, based on Extreme Learning Machine (ELM) and HOG descriptor, to classify by form and content. A database of Ecuadors regulatory traffic signs has also been created. It has more than 47,000 images of Ecuadorian road signs divided into 16 classes. The experimental results, from the recognition module, generate an accuracy of 99,85 %, and a sensitivity of 99,78 % in the first stage, and an accuracy of 96,71 % and a sensitivity of 94,16 % in the second stage. In addition, its robustness was compared with two other classifiers, in order to choose the one with the best performance in terms of accuracy and low computational cost. This system works at 24 frames per second, and it was tested in real driving conditions, from 6:00 a.m. until 7:00 p.m., on the streets of several cities and highways of Ecuador.

Adaptive fuzzy weighted color histogram and HOG appearance model for object tracking with a dynamic trained neural network prediction

Object tracking in video sequences represents an important task in computer vision applications like human mobility and social distance in pandemic scenarios, intelligent surveillance systems, etc. This paper presents a new method, fuzzy weighted color histogram neural network (FWCHNN) to estimate the position of an object and to update the appearance object model during tracking. The method involves two stages. Prediction is achieved through an online dynamic trained neural network, and correction is performed with a spiral sliding window. The method employs a new similitude appearance measure based on a codified model of the object considering its shape and color. The shape is represented with HOG features and the color features from information of a fuzzy weighted color histogram. FWCHNN shows the comparable results regarding state-of-the-art methods.

Isolated Handwritten Pashto Character Recognition Using a K-NN Classification Tool based on Zoning and HOG Feature Extraction Techniques

Handwritten text recognition is considered as the most challenging task for the research community due to slight change in different characters’ shape in handwritten documents. The unavailability of a standard dataset makes it vaguer in nature for the researchers to work on. To address these problems, this paper presents an optical character recognition system for the recognition of offline Pashto characters. The problem of the unavailability of a standard handwritten Pashto characters database is addressed by developing a medium-sized database of offline Pashto characters. This database consists of 11352 character images (258 samples for each 44 characters in a Pashto script). Enriched feature extraction techniques of histogram of oriented gradients and zoning-based density features are used for feature extraction of carved Pashto characters. K-nearest neighbors is considered as a classification tool for the proposed algorithm based on the proposed feature sets. A resultant accuracy of 80.34% is calculated for the histogram of oriented gradients, while for zoning-based density features, 76.42% is achieved using 10-fold cross validation.

RETRACTED ARTICLE: Pedestrian identification using motion-controlled deep neural network in real-time visual surveillance

In the computer vision applications such as security surveillance and robotics, pedestrian identification shows much attention in the last decade. This is usually achieved by human biometrics. Besides human biometrics, sometimes it is required to identify pedestrians at a distance. This could be accomplished based on a fact of different whole-body appearances. The real-time pedestrian identification is a challenging task due to several factors such as illumination effects, noise, change in viewpoint, and video resolution. The more recent, the deep neural network (DNN) shows a massive performance for various real-world applications. In this article, we present a real-time architecture for pedestrian identification using motion-controlled DNN. In the proposed architecture, the motion vectors are calculating using optical flow and then utilized in the next step, named features extraction. Two types of features, such as HOG and DNN, are computing. The pre-trained VGG19 CNN model is employing and trained through transfer learning. The deep learning features are extracted from two layers—fully connected layers 7 and 8. Also, we proposed a feature selection method named Bayesian modeling along with LSVM. The best selected features of both HOG and DNN are finally fused in one matrix for final identification. The multi-class support vector machine classifier is used for final identification. The videos are recording in the real-time environment for the experimental process and achieve an average accuracy of 98.62%. Overall, identification accuracy shows the effectiveness of the proposed approach.

Convolutional Neural Network Based on HOG Feature for Bird Species Detection and Classification

Convolutional Neural Network Based on HOG Feature for Bird Species Detection and Classification

Optimized Scale Invariant HOG Descriptors for Object and Human Detection

This article presents a scale variation approach to identify objects and humans in video sequences using histogram of gradient descriptor. A significant restriction in HOG descriptors is its variations with scale changes and illumination changes, as is frequently the considered case. We recommend unique SIO-HOG descriptors that are figured to be invariant to scale changes. The system associates the benefits of adoptive bin selections and sample resizing in the object recognition process. We analyze the effect of PCA transform based feature selection process on object detection performance, ultimately the finite scale range, adoptive orientation binning in non-overlapping descriptors is all main thing for nominal detection rate. HOG feature vector over complete search window is computationally more exclusive, to acquire more precise set of features with finite Euclidean distance to classify them using KNN classifier. This new approach provides near-perfect ways of separating humans from other objects. The whole object detection system was assessed on a few test samples from real-world data sets and compared beside a publicly available pedestrian detection data base.

Intelligent pointer meter interconnection solution for data collection in farmlands

Some non-digitized measuring instruments such as pointer meters are utilized by some farmlands by virtue of their high stability and accuracy, and the data collection depending on the human movements requires considerable time and effort and has a low technology level. Therefore, an intelligent pointer meter indication reading and automatic collection method is proposed using machine vision and wireless sensor network (WSN) technology. An intelligent pointer meter indication reading device consisting of an image acquisition module, an intelligent control center, a wireless transmission module, and a power module was developed, which could accomplish intelligent meter indication reading and automatic data uploading. Furthermore, a pointer meter indication reading algorithm for a resource-limited environment is proposed. Firstly, the pointer and the circle axis were recognized by using edge detection and the geometrical characteristics of the pointer meter, and then, the scales and scale values were determined using the statistical characteristics of the circles around the pointer’s vertex. Next, by utilizing the density-based spatial clustering of applications with noise (DBSCAN) algorithm, we adjusted the scales and the scale values, taking full advantage of the pointer’s characteristic that the scales’ rotation angles changed linearly with the scale values, which were classified by an SVM taking in the HOG feature as the input. Finally, the indication was computed in terms of the relative position of the pointer between the adjacent scale values, and the accuracy was 94.2%. The proposed method was evaluated by comparing it with some newly published algorithms. The pointer detection method had stronger robustness and anti-interference capability than the image segmentation method and the skeleton extraction method. The Θ(n) value, indicating the complexity of the scale detection algorithm, was considerably smaller than the Θ(n2) value, denoting the modified central mapping method used mostly for scale detection. The energy consumption by each module was measured, and the results showed that the image acquisition module accounted for the largest energy consumption, 87.7%, which was more than eight times as much as the second-largest energy consumption, 10.3% (that of the wireless transmission module); the problem of power supply could be solved by using solar panels.

Ovarian Tumor Texture Classification Based on Sparse Auto-Encoder Network Combined with Multi-Feature Fusion and Random Forest in Ultrasound Image

Texture analysis has always been active areas of ultrasound image processing research. Using texture features to classify the ultrasound images is the focus of researchers' attention. How to extract representative texture features is an important part of successful texture description. The research goal of this paper is to apply the deep neural network into the ultrasound classification of ovarian tumors, and design a novel type of ovarian cancer diagnosis system. The improved HOG feature extraction method and the gray-level concurrence matrix of LBP image are firstly adopted to extract low-level features; Then, these features are cascaded into a new feature vector, and are input into the auto-encoder neural network to learn the high-level feature. Finally, the SVM classifier is used to achieve the classification of ovarian lesion. A large number of qualitative and quantitative experiments show that the improved method has more performance than the comparisons algorithms for ovarian ultrasound lesion, and it can significantly improve the classification performance while ensuring the accuracy rate and recall rate.