Showing papers on "Histogram of oriented gradients published in 2020"

Invariant Attribute Profiles: A Spatial-Frequency Joint Feature Extractor for Hyperspectral Image Classification

Abstract: So far, a large number of advanced techniques have been developed to enhance and extract the spatially semantic information in hyperspectral image processing and analysis. However, locally semantic change, such as scene composition, relative position between objects, spectral variability caused by illumination, atmospheric effects, and material mixture, has been less frequently investigated in modeling spatial information. Consequently, identifying the same materials from spatially different scenes or positions can be difficult. In this article, we propose a solution to address this issue by locally extracting invariant features from hyperspectral imagery (HSI) in both spatial and frequency domains, using a method called invariant attribute profiles (IAPs). IAPs extract the spatial invariant features by exploiting isotropic filter banks or convolutional kernels on HSI and spatial aggregation techniques (e.g., superpixel segmentation) in the Cartesian coordinate system. Furthermore, they model invariant behaviors (e.g., shift, rotation) by the means of a continuous histogram of oriented gradients constructed in a Fourier polar coordinate. This yields a combinatorial representation of spatial-frequency invariant features with application to HSI classification. Extensive experiments conducted on three promising hyperspectral data sets (Houston2013 and Houston2018) to demonstrate the superiority and effectiveness of the proposed IAP method in comparison with several state-of-the-art profile-related techniques. The codes will be available from the website: https://sites.google.com/view/danfeng-hong/data-code .

Deep learning for lung Cancer detection and classification

Abstract: Lung cancer is one of the main reasons for death in the world among both men and women, with an impressive rate of about five million deadly cases per year. Computed Tomography (CT) scan can provide valuable information in the diagnosis of lung diseases. The main objective of this work is to detect the cancerous lung nodules from the given input lung image and to classify the lung cancer and its severity. To detect the location of the cancerous lung nodules, this work uses novel Deep learning methods. This work uses best feature extraction techniques such as Histogram of oriented Gradients (HoG), wavelet transform-based features, Local Binary Pattern (LBP), Scale Invariant Feature Transform (SIFT) and Zernike Moment. After extracting texture, geometric, volumetric and intensity features, Fuzzy Particle Swarm Optimization (FPSO) algorithm is applied for selecting the best feature. Finally, these features are classified using Deep learning. A novel FPSOCNN reduces computational complexity of CNN. An additional valuation is performed on another dataset coming from Arthi Scan Hospital which is a real-time data set. From the experimental results, it is shown that novel FPSOCNN performs better than other techniques.

Deep neural network based Rider-Cuckoo Search Algorithm for plant disease detection

Abstract: Agriculture is the main source of wealth, and its contribution is essential to humans. However, several obstacles faced by the farmers are due to different kinds of plant diseases. The determination and anticipation of plant diseases are the major concerns and should be considered for maximizing productivity. This paper proposes an effective image processing method for plant disease identification. In this research, the input image is subjected to the pre-processing phase for removing the noise and artifacts present in the image. After obtaining the pre-processed image, it is subjected to the segmentation phase for obtaining the segments using piecewise fuzzy C-means clustering (piFCM). Each segment undergoes a feature extraction phase in which the texture features are extracted, which involves information gain, histogram of oriented gradients (HOG), and entropy. The obtained texture features are subjected to the classification phase, which uses the deep belief network (DBN). Here, the proposed Rider-CSA is employed for training the DBN. The proposed Rider-CSA is designed by integrating the rider optimization algorithm (ROA) and Cuckoo Search (CS). The experimental results proved that the proposed Rider-CSA-DBN outperformed other existing methods with maximal accuracy of 0.877, sensitivity of 0.862, and the specificity of 0.877, respectively.

Comparison of Viola-Jones Haar Cascade Classifier and Histogram of Oriented Gradients (HOG) for face detection

Abstract: Human face recognition is one of the most challenging topics in the areas of image processing, computer vision, and pattern recognition. Before recognizing the human face, it is necessary to detect a face then extract the face features. Many methods have been created and developed in order to perform face detection and two of the most popular methods are Viola-Jones Haar Cascade Classifier (V-J) and Histogram of Oriented Gradients (HOG). This paper proposed a comparison between VJ and HOG for detecting the face. V-J method calculate Integral Image through Haar-like feature with AdaBoost process to make a robust cascade classifier, HOG compute the classifier for each image in and scale of the image, applied the sliding windows, extracted HOG descriptor at each window and applied the classifier, if the classifier detected an object with enough probability that resembles a face, the classifier recording the bounding box of the window and applied non-maximum suppression to make the accuracy increased. The experimental results show that the system successfully detected face based on the determined algorithm. That is mean the application using computer vision can detect face and compare the results.

Transfer Deep Learning Along With Binary Support Vector Machine for Abnormal Behavior Detection

Abstract: Today, machine learning and deep learning have paved the way for vital and critical applications such as abnormal detection. Despite the modernity of transfer learning, it has proved to be one of the crucial inventions in the field of deep learning because of its promising results. For the purpose of this study, transfer learning is utilized to extract human motion features from RGB video frames to improve detection accuracy. A convolutional neural network (CNN) based on Visual Geometry Group network 19 (VGGNet-19) pre-trained model is used to extract descriptive features. Next, the feature vector is passed into Binary Support Vector Machine classifier (BSVM) to construct a binary-SVM model. The performance of the proposed framework is evaluated by three parameters: accuracy, area under the curve, and equal error rate. Experiments performed on two different datasets comprising highly different context abnormalities accomplished an accuracy of 97.44% and an area under the curve (AUC) of 0.9795 for University of Minnesota (UMN) dataset and accomplished an accuracy of 86.69% and an AUC of 0.7987 for University of California, San Diego Pedistrain1 (UCSD-PED1) dataset. Moreover, the performance of the pre-trained network VGGNet-19 with handcrafted feature descriptors and with other CNN pre-trained networks, respectively, has been investigated in this study for abnormal behavior detection. The results demonstrated that VGGNet-19 has better performance than histogram of oriented gradients, background subtraction, and optical flow. In addition, the VGGNet-19 shows higher detection accuracy than other pre-trained networks: GoogleNet, ResNet50, AlexNet, and VGGNet-16.

Histogram of Oriented Gradients Feature Extraction From Raw Bayer Pattern Images

Abstract: This brief studies the redundancy in the image processing pipeline for histogram of oriented gradients (HOG) feature extraction. The impact of demosaicing on the extracted HOG features is analyzed and experimented. It is shown that by taking advantage of the inter-channel correlation of natural images, the HOG features can be directly extracted from the Bayer pattern images with proper gamma compression. Due to the elimination of the image processing pipeline, the power consumption and computational complexity of the detection system can be significantly reduced. Experimental results show that the Bayer pattern image-based HOG features can be used in pedestrian detection systems with little performance degradation.

Feature Selection for Facial Emotion Recognition Using Cosine Similarity-Based Harmony Search Algorithm

Abstract: Nowadays, researchers aim to enhance man-to-machine interactions by making advancements in several domains. Facial emotion recognition (FER) is one such domain in which researchers have made significant progresses. Features for FER can be extracted using several popular methods. However, there may be some redundant/irrelevant features in feature sets. In order to remove those redundant/irrelevant features that do not have any significant impact on classification process, we propose a feature selection (FS) technique called the supervised filter harmony search algorithm (SFHSA) based on cosine similarity and minimal-redundancy maximal-relevance (mRMR). Cosine similarity aims to remove similar features from feature vectors, whereas mRMR was used to determine the feasibility of the optimal feature subsets using Pearson’s correlation coefficient (PCC), which favors the features that have lower correlation values with other features—as well as higher correlation values with the facial expression classes. The algorithm was evaluated on two benchmark FER datasets, namely the Radboud faces database (RaFD) and the Japanese female facial expression (JAFFE). Five different state-of-the-art feature descriptors including uniform local binary pattern (uLBP), horizontal–vertical neighborhood local binary pattern (hvnLBP), Gabor filters, histogram of oriented gradients (HOG) and pyramidal HOG (PHOG) were considered for FS. Obtained results signify that our technique effectively optimized the feature vectors and made notable improvements in overall classification accuracy.

Comparative Study on Deep Convolution Neural Networks DCNN-Based Offline Arabic Handwriting Recognition

Abstract: Recently, deep learning techniques demonstrated efficiency in building better performing machine learning models which are required in the field of offline Arabic handwriting recognition. Our ancient civilizations presented valuable handwritten manuscripts that need to be documented digitally. If we compared between Latin and the isolated Arabic character recognition, the latter is much more challenging due to the similarity between characters, and the variability of the writing styles. This paper proposes a multi-stage cascading system to serve the field of offline Arabic handwriting recognition. The approach starts with applying the Hierarchical Agglomerative Clustering (HAC) technique to split the database into partially inter-related clusters. The inter-relations between the constructed clusters support representing the database as a big search tree model and help to attain a reduced complexity in matching each test image with a cluster. Cluster members are then ranked based on our new proposed ranking algorithm. This ranking algorithm starts with computing Pyramid Histogram of Oriented Gradients (PHoG), and is followed by measuring divergence by Kullback-Leibler method. Eventually, the classification process is applied only to the highly ranked matching classes. A comparative study is made to assess the effect of six different deep Convolution Neural Networks (DCNNs) on the final recognition rates of the proposed system. Experiments are done using the IFN/ENIT Arabic database. The proposed clustering and ranking stages lead to using only 11% of the whole database in classifying test images. Accordingly, more reduced computation complexity and more enhanced classification results are achieved compared to recent existing systems.

Enhanced pedestrian detection using optimized deep convolution neural network for smart building surveillance

Abstract: Pedestrian detection and tracking is a critical task in the area of smart building surveillance. Due to advancements in sensors, the architects concentrate in construction of smart buildings. Pedestrian detection in smart building is greatly challenged by the image noises by various external environmental parameters. Traditional filter-based techniques for image classification like histogram of oriented gradients filters and machine learning algorithms suffer to perform well for huge volume of pedestrian input images. The advancements in deep learning algorithms perform exponentially good in handling the huge volume of image data. The current study proposes a pedestrian detection model based on deep convolution neural network (CNN) for classification of pedestrians from the input images. Proposed optimized version of VGG-16 architecture is evaluated for pedestrian detection on the INRIA benchmarking dataset consisting of 227 × 227 pixel images. The proposed model achieves an accuracy of 98.5%. It was found that proposed model performs better than the other pretrained CNN architectures and other machine learning models. Pedestrians are reasonably detected and the performance of the proposed algorithm is validated.

A multidimensional chaotic image encryption algorithm based on the region of interest

Abstract: Most image encryption algorithms encrypt the whole image, but only part of the data is important in the image. In this paper, we propose a multidimensional chaotic image encryption algorithm based on the region of interest (ROI). The histogram of oriented gradients (HOG) feature extraction and support vector machine (SVM) are used to separate the region of interest from the whole image. Then, the region of interest pixels is messed up by using the improved Henon sequence, Joseph sequence and the region of interest pixels are diffused by using the unified chaotic sequence to hide the sensitive information in the image, so as to achieve the purpose of private protection. Furthermore, the improved logistic sequence is used to hide the edge information of the target image to achieve the tradeoff between the secrecy of information and the complexity of encryption. A series of analyses are carried out including key space analysis, key sensitivity analysis, statistical analysis, information entropy analysis, analysis of the fixed-point obscuration analysis, quality analysis and image decryption for our encryption algorithm. Through experiments and comparisons, the proposed algorithm has good performance in encrypting image and coping with various invasions. The image encryption algorithm based on ROI has a good performance of security, moreover through the main encryption of ROI can effectively shorten the encryption time, so as to achieve the compromise of security and computational complexity.

A Survey on Artificial Intelligence in Chinese Sign Language Recognition

Abstract: Chinese Sign Language (CSL) offers the main means of communication for the hearing impaired in China. Sign Language Recognition (SLR) can shorten the distance between the hearing-impaired and healthy people and help them integrate into the society. Therefore, SLR has become the focus of sign language application research. Over the years, the continuous development of new technologies provides a source and motivation for SLR. This paper aims to cover the most recent approaches in Chinese Sign Language Recognition (CSLR). With a thorough review of superior methods from 2000 to 2019 in CSLR researches, various techniques and algorithms such as scale-invariant feature transform, histogram of oriented gradients, wavelet entropy, Hu moment invariant, Fourier descriptor, gray-level co-occurrence matrix, dynamic time warping, principal component analysis, autoencoder, hidden Markov model (HMM), support vector machine (SVM), random forest, skin color modeling method, k-NN, artificial neural network, convolutional neural network (CNN), and transfer learning are discussed in detail, which are based on several major stages, that is, data acquisition, preprocessing, feature extraction, and classification. CSLR was summarized from some aspect as follows: methods of classification and feature extraction, accuracy/performance evaluation, and sample size/datasets. The advantages and limitations of different CSLR approaches were compared. It was found that data acquisition is mainly through Kinect and camera, and the feature extraction focuses on hand’s shape and spatiotemporal factors, but ignoring facial expressions. HMM and SVM are used most in the classification. CNN is becoming more and more popular, and a deep neural network-based recognition approach will be the future trend. However, due to the complexity of the contemporary Chinese language, CSLR generally has a lower accuracy than other SLR. It is necessary to establish an appropriate dataset to conduct comparable experiments. The issue of decreasing accuracy as the dataset increases needs to resolve. Overall, our study is hoped to give a comprehensive presentation for those people who are interested in CSLR and SLR and to further contribute to the future research.

Plant species identification from leaf patterns using histogram of oriented gradients feature space and convolution neural networks

Abstract: The determination of plant species from field observation requires substantial botanical expertise, which puts it beyond the reach of most nature enthusiasts. Traditional plant species identificati...

Conflict analytics through the vehicle safety space in mixed traffic flows using UAV image sequences

Abstract: The mixed traffic flow has complex dynamics by nature. The kinematic differences between automobiles and motorcycles result to distinct driving behaviors. Traditional automobile-based traffic flow theory is not always suitable for mixed traffic streams. The purpose of this study is to observe from actual data a clearance boundary, called Safety Space, drivers maintain from other vehicles, and use it as a spatial filter to determine conflicts in mixed traffic flows. Image data are collected from an Unmanned Aerial Vehicle (UAV), and microscopic characteristics such as vehicle type, position, velocity, and trajectory are extracted through computer vision techniques. The Histogram of Oriented Gradients (HOG) feature and the Support Vector Machine (SVM) classifier are utilized for the vehicle detection, while the Kalman Filter is employed for the derivation of vehicle trajectories. The Safety Space is then determined based on those trajectories. Validation data are collected at intersections in Taipei, Taiwan; Bangkok, Thailand; and Mumbai, India. The vehicle detection and tracking are satisfactory, and the Safety Space surrogate reveals risk zones caused by spatial proximity between vehicles.

Recognition of basketball referee signals from real-time videos

Abstract: Recognition of hand gestures (hand signals) is an active research area for human computer interaction with many possible applications. Automatic machine vision-based hand gesture interfaces for real-time applications require fast and extremely robust human, pose and hand detection, and gesture recognition. Attempting to recognize gestures performed by official referees in sports (such as basketball game) video places tough requirements on the image segmentation techniques. Here we propose an image segmentation technique based on the histogram of oriented gradients and local binary pattern (LBP) features, which allow recognizing the signals of basketball referee from recorded game videos and achieved an accuracy of 95.6% using LBP features and support vector machine for classification. Our results are relevant for real-time analysis of basketball game.

A Histogram of Oriented Gradients Approach for Detecting Broken Bars in Squirrel-Cage Induction Motors

Abstract: This article presents a novel approach for detecting broken rotor bars in squirrel-cage induction motors, using a time-domain current analysis. More particularly, this solution proposes a new use of histogram of oriented gradients since this method is usually applied in computer vision and image processing applications. Fully broken rotor bars have been detected when the motor was running at a very low slip since this operational condition is very difficult to identify using the traditional motor-current signature analysis. In addition, only one phase of the stator current of the machine was applied to extract the intensity gradients and edge directions of each current time window, for both healthy and damaged rotors. It is important to highlight that the present method does not require the slip measurement for fault detection, as demand for other techniques and often related to false negative indications. The features extracted from the histograms have been applied as inputs for a neural network classifier. This method has been validated using some experimental data from a 7.5-kW squirrel-cage induction machine running at distinct load levels (slip conditions) and also for oscillatory loads.

Cursive Character Recognition in Natural Scene Images Using a Multilevel Convolutional Neural Network Fusion

Abstract: The accuracy of current natural scene text recognition algorithms is limited by the poor performance of character recognition methods for these images. The complex backgrounds, variations in the writing, text size, orientations, low resolution and multi-language text make recognition of text in natural images a complex and challenging task. Conventional machine learning and deep learning-based methods have been developed that have achieved satisfactory results, but character recognition for cursive text such as Arabic and Urdu scripts in natural images is still an open research problem. The characters in the cursive text are connected and are difficult to segment for recognition. Variations in the shape of a character due to its different positions within a word make the recognition task more challenging than non-cursive text. Optical character recognition (OCR) techniques proposed for Arabic and Urdu scanned documents perform very poorly when applied to character recognition in natural images. In this paper, we propose a multi-scale feature aggregation (MSFA) and a multi-level feature fusion (MLFF) network architecture to recognize isolated Urdu characters in natural images. The network first aggregates multi-scale features of the convolutional layers by up-sampling and addition operations and then combines them with the high-level features. Finally, the outputs of the MSFA and MLFF networks are fused together to create more robust and powerful features. A comprehensive dataset of segmented Urdu characters is developed for the evaluation of the proposed network models. Synthetic text on the patches of images with real natural scene backgrounds is generated to increase the samples of infrequently used characters. The proposed model is evaluated on the Chars74K and ICDAR03 datasets. To validate the proposed model on the new Urdu character image dataset, we compare its performance with the histogram of oriented gradients (HoG) method. The experimental results show that the aggregation of multi-scale and multilevel features and their fusion is more effective, and outperforms other methods on the Urdu character image and Chars74K datasets.

Exposing video inter-frame forgery via histogram of oriented gradients and motion energy image

Abstract: Inter-frame forgery is a common type of video forgery to destroy the video evidence. It occurs in the temporal domain such as frame deletion, frame insertion, frame duplication, and frame shuffling. These forms of forgery are more frequently produced in a surveillance video because the camera position and the scene are relatively stable, where the tampering process is easy to operate and imperceptible. In this paper, we propose an efficient method for inter-frame forgery detection based on histogram of oriented gradients (HOG) and motion energy image (MEI). HOG is obtained from each image as a discriminative feature. In order to detect frame deletion and insertion, the correlation coefficients are used and abnormal points are detected via Grabb’s test. In addition, MEI is applied to edge images of each shot to detect frame duplication and shuffling. Experimental results prove that the proposed method can detect all inter-frame forgeries and achieve higher accuracy with lower execution time.

Optical Character Recognition using Ensemble of SVM, MLP and Extra Trees Classifier

Abstract: This paper deals with retrieval of contents of any printed or handwritten document. Maximally Stable Extremal Regions (MSER) algorithm along with region-growing methods are used for the detection of printed regions. Histogram of Oriented Gradients (HOG features) are used for feature extraction. Various machine learning algorithms, namely Decision Trees, Random Forest, Extra Trees Classifier, MLP, and SVM along with ensemble method were used for classification, and the accuracies compared.

Fusion of deep-learned and hand-crafted features for cancelable recognition systems

Abstract: The recent years have witnessed a dramatic shift in the way of biometric identification, authentication, and security processes. Among the essential challenges that face these processes are the online verification and authentication. These challenges lie in the complexity of such processes, the necessity of the personal real-time identifiable information, and the methodology to capture temporal information. In this paper, we present an integrated biometric recognition method to jointly recognize face, iris, palm print, fingerprint and ear biometrics. The proposed method is based on the integration of the extracted deep-learned features together with the hand-crafted ones by using a fusion network. Also, we propose a novel convolutional neural network (CNN)-based model for deep feature extraction. In addition, several techniques are exploited to extract the hand-crafted features such as histogram of oriented gradients (HOG), oriented rotated brief (ORB), local binary patterns (LBPs), scale-invariant feature transform (SIFT), and speeded-up robust features (SURF). Furthermore, for dimensional consistency between the combined features, the dimensions of the hand-crafted features are reduced using independent component analysis (ICA) or principal component analysis (PCA). The core of this paper is the template protection via a cancelable biometric scheme without significantly affecting the recognition performance. Specifically, we have used the bio-convolving approach to enhance the user’s privacy and ensure the robustness against spoof attacks. Additionally, various CNN hyper-parameters with their impact on the proposed model performance are studied. Our experiments on various datasets revealed that the proposed method achieves 96.69%, 95.59%, 97.34%, 96.11% and 99.22% recognition accuracies for face, iris, fingerprint, palm print and ear recognition, respectively.

Human gait recognition based on histogram of oriented gradients and Haralick texture descriptor

Abstract: Gait recognition is an evolving technology in the biometric domain; it aims to recognize people through an analysis of their walking pattern. One of the significant challenges of the appearance-based gait recognition system is to augment its performance by using a distinctive low-dimensional feature vector. Therefore, this study proposes the low-dimensional features that are capable of effectively capturing the spatial, gradient, and texture information in this context. These features are obtained by the computation of histogram of oriented gradients, followed by sum variance Haralick texture descriptor from nine cells of gait gradient magnitude image. Further, the performance of the proposed method is validated on five widely used gait databases. They include CASIA A gait database, CASIA B gait database, OU-ISIR D gait database, CMU MoBo database, and KTH video database. The experimental results demonstrated that the proposed approach could choose significant discriminatory features for individual identification and consequently, outperform certain state-of-the-art methods in terms of recognition performance.