Orientation Histogram Research Articles

A Novel Approach for Pose Invariant Face Recognition in Surveillance Videos

The face detection and face recognition methods are introduced to confirm the abnormal human activity in the video surveillance system. Face detection is carried out by Viola-Jones face detector. It is composed of three concepts namely integral image, AdaBoost and the cascade structure. After face detection, Histogram of Oriented Gradient(HOG) and Weighted Local Binary Patterns(WLBP) features are extracted and those are used in Orthogonal Locality Preserving Projection(OLPP) for face recognition. The detected faces may contain pose variation which dramatically degrades the OLPP based face recognition. So, pose-invariant OLLP-based face recognition is proposed where Histogram of Face Orientation(HFO) and Histogram of Face Direction(HFD), HOG and WLBP features are used in OLPP for efficient face recognition.

Virtual Reality Image Technology Assists Training Optimization of Motion Micro-Time Scale

Virtual reality image local features are highly repetitive and are not easily affected by target occlusion, so research on virtual reality image local feature extraction techniques has received increasing attention. For the purpose of global scale selection, this article considers the virtual reality image in the global scope from the theoretical perspectives of the continuity of virtual reality images, the repeatability of virtual reality image features, the scale of scene virtual reality images in the global scope, and the visual saliency. This paper gives a general framework of multi-scale geometric analysis and particle swarm optimization virtual reality image matching algorithm. For the problem of virtual reality image matching, the original particle swarm optimization algorithm is improved. A more reasonable inertia weight change formula, a method for selecting the optimal solution when two objectives are optimized at the same time, and a method for selecting a reasonable input are designed. In this paper, performance evaluation experiments are performed on several feature description algorithms. The experimental results show that the descriptors constructed by these feature description algorithms are significantly more robust than SIFT (Scale Invariant Feature Transform) descriptors. The improved multi-scale geometric analysis and particle swarm optimization are robust due to the introduction of multiple support domains. It has the best discriminative ability, but at the same time, the introduction of multiple support domains leads to the worst real-time algorithm; DGOH (Dual Gradient Orientation Histogram) algorithm is more robust than FRDOH (Fast Repre-sentation Based on a Double Orientation Histogram) and SIFT algorithm, and DGOH algorithm has the best real-time performance.

Analysis of Galactic molecular cloud polarization maps: a review of the methods

The Davis-Chandrasekhar-Fermi (DCF) method using the Angular Dispersion Function (ADF), the Histogram of Relative Orientations (HROs) and the Polarization-Intensity Gradient Relation (P-IGR) are the most common tools used to analyse maps of linearly polarized emission by thermal dust grains at submilliter wavelengths in molecular clouds and star-forming regions. A short review of these methods is given. The combination of these methods will provide valuable tools to shed light on the impact of the magnetic fields on the formation and evolution of subparsec scale hub-filaments that will be mapped with the NIKA2 camera and future experiments.

Abnormal Infant Movements Classification With Deep Learning on Pose-Based Features

The pursuit of early diagnosis of cerebral palsy has been an active research area with some very promising results using tools such as the General Movements Assessment (GMA). In our previous work, we explored the feasibility of extracting pose-based features from video sequences to automatically classify infant body movement into two categories, normal and abnormal. The classification was based upon the GMA, which was carried out on the video data by an independent expert reviewer. In this paper we extend our previous work by extracting the normalised pose-based feature sets, Histograms of Joint Orientation 2D (HOJO2D) and Histograms of Joint Displacement 2D (HOJD2D), for use in new deep learning architectures. We explore the viability of using these pose-based feature sets for automated classification within a deep learning framework by carrying out extensive experiments on five new deep learning architectures. Experimental results show that the proposed fully connected neural network FCNet performed robustly across different feature sets. Furthermore, the proposed convolutional neural network architectures demonstrated excellent performance in handling features in higher dimensionality. We make the code, extracted features and associated GMA labels publicly available.

A Fast and Efficient CAD System for Improving the Performance of Malignancy Level Classification on Lung Nodules

Accurate malignancy level classification of lung nodules can reduce lung cancer mortality rate effectively. In this study, we present a fast and efficient CAD system to improve the performance of nodules malignancy level classification. Firstly, to reduce false positives (FPs), we propose a novel vessel segmentation method which measures vessel likelihood by tubular-like structures discriminating from multiple views. The method can recognize irregular vascular structures robustly and sensitively, and achieve fast vessel segmentation. In addition, a mathematical description for 3D pulmonary entities using neighbor centroids clustering is provided as a fundamental condition for spatial feature extraction. To optimize features extraction, we formulate a gray values cumulative function and a patches selection function based on the mathematical description, to generate axial spatial outline and spatial density distribution samples of the entities, respectively. Then, we use Edge Orientation Histogram (EOH) to extract edge features from the spatial outline and propose a multi-scale path LBP (MSPLBP) to extract the texture feature of the density distribution samples. Finally, the fused EOH and MSPLBP are classified into 6 malignancy levels by three state-of-the-art classifiers. The experimental results show that the vessel segmentation method achieves an average $F1\_Score$ of 78.14% and AUC value under $PR$ curves of 0.8149. Moreover, our system reaches an average $accuracy$ of 95.88% and consumes average 176.26 seconds for evaluating a CT set on malignancy level classification. These results indicate that the system can segment vessels exactly, and classify the malignancy level of nodules efficiently. Our system is the potential to be a powerful tool for early diagnosis of lung cancer.

Road Extraction From High-Resolution Satellite Images Based on Multiple Descriptors

Geometry and texture noise make it difficult to accurately describe road image rules, which leads to the low degree of automation of traditional template matching algorithms based on internal texture homogenization. We propose a semi-automatic road extraction method based on multiple descriptors to improve the degree of automation while ensuring the accuracy of road extraction. This method aims to address the problems of incomplete road image geometric information and poor homogeneity of internal road texture. The multiscale line segment orientation histogram model and sector descriptor are established. Road points are tracked by interpolation and extension, and postprocessing is used to fit the tracking points and extract the road routes. In this article, high-resolution remote sensing images of different types, different resolutions, and different scenes are selected, and the roads exhibit curvatures, vehicle and shadow occlusions, roundabouts, and variational features. Experiments show that for roads with a certain width, completeness, and correctness of the method are more than 98%. Additionally, as compared with other algorithms, the interactive human intervention of this method is reduced by more than 2/3.

A Facial Expression Recognition Model using Hybrid Feature Selection and Support Vector Machines

Facial expression recognition is a challenging issue in the field of computer vision. Due to the limited feature extraction capability of a single feature descriptor, in this paper, a hybrid feature extraction is utilised. The proposed methodology includes local and global feature extractions that is done by local binary pattern (LBP) and histogram orientation gradient (HOG) respectively. Before applying the feature extraction process, pre-processing and face detection is applied on the face image to extract the useful features. The Viola and Jones algorithm is utilised for face detection and the hybrid Laplacian of Gaussian (HLOG) is used for pre-processing stage. The orthogonal local preserving projection (OLPP)-based dimension reduction algorithm is applied to the extracted features to minimise the computational complexity of the classification algorithm. The SVM classification algorithm is utilised for identifying the facial expression. Here, standard CK+ facial expression dataset is used for evaluating the proposed methodology. The proposed methodology performed well in terms of accuracy compared to the existing PCA + Gabor and PCA + LBP methodology.

A comprehensive study on feature types for osteoporosis classification in dental panoramic radiographs

Background and ObjectiveOsteoporosis is a disease characterized by a decrease in bone density. It is often associated with fractures and severe pain. Previous studies have shown a high correlation between the density of the bone in the hip and in the mandibular bone in the jaw. This suggests that dental radiographs might be useful for detecting osteoporosis. Use of dental radiographs for this purpose would simplify early detection of osteoporosis. However, dental radiographs are not normally examined by radiologists. This paper explores the use of 13 different feature extractors for detection of reduced bone density in dental radiographs. MethodsThe computed feature vectors are then processed with a Self-Organizing Map and Learning Vector Quantization as well as Support Vector Machines to produce a set of 26 predictive models. ResultsThe results show that the models based on Self-Organizing Map and Learning Vector Quantization using Gabor Filter, Edge Orientation Histogram, Haar Wavelet, and Steerable Filter feature extractors outperform the rest of the 22 models in detecting osteoporosis. The proposed Gabor-based algorithm achieved an accuracy of 92.6%, a sensitivity of 97.1%, and a specificity of 86.4%. ConclusionsThe oriented edges and textures in the upper and lower jaw regions are useful for distinguishing normal patients from patients with osteoporosis.

Droplets. II. Internal Velocity Structures and Potential Rotational Motions in Pressure-dominated Coherent Structures

Abstract We present an analysis of the internal velocity structures of the newly identified sub-0.1 pc coherent structures, droplets, in L1688 and B18. By fitting 2D linear velocity fields to the observed maps of velocity centroids, we determine the magnitudes of linear velocity gradients and examine the potential rotational motions that could lead to the observed velocity gradients. The results show that the droplets follow the same power-law relation between the velocity gradient and size found for larger-scale dense cores. Assuming that rotational motion giving rise to the observed velocity gradient in each core is a solid-body rotation of a rotating body with a uniform density, we derive the “net rotational motions” of the droplets. We find a ratio between rotational and gravitational energies, β, of ∼0.046 for the droplets, and when including both droplets and larger-scale dense cores, we find β ∼ 0.039. We then examine the alignment between the velocity gradient and the major axis of each droplet, using methods adapted from the histogram of relative orientations introduced by Soler et al. We find no definitive correlation between the directions of velocity gradients and the elongations of the cores. Lastly, we discuss physical processes other than rotation that may give rise to the observed velocity field.

Automatic identification and autonomous sorting of cylindrical parts in cluttered scene based on monocular vision 3D reconstruction

Purpose This paper aims to propose an identification method based on monocular vision for cylindrical parts in cluttered scene, which solves the issue that iterative closest point (ICP) algorithm fails to obtain global optimal solution, as the deviation from scene point cloud to target CAD model is huge in nature. Design/methodology/approach The images of the parts are captured at three locations by a camera amounted on a robotic end effector to reconstruct initial scene point cloud. Color signatures of histogram of orientations (C-SHOT) local feature descriptors are extracted from the model and scene point cloud. Random sample consensus (RANSAC) algorithm is used to perform the first initial matching of point sets. Then, the second initial matching is conducted by proposed remote closest point (RCP) algorithm to make the model get close to the scene point cloud. Levenberg Marquardt (LM)-ICP is used to complete fine registration to obtain accurate pose estimation. Findings The experimental results in bolt-cluttered scene demonstrate that the accuracy of pose estimation obtained by the proposed method is higher than that obtained by two other methods. The position error is less than 0.92 mm and the orientation error is less than 0.86°. The average recognition rate is 96.67 per cent and the identification time of the single bolt does not exceed 3.5 s. Practical implications The presented approach can be applied or integrated into automatic sorting production lines in the factories. Originality/value The proposed method improves the efficiency and accuracy of the identification and classification of cylindrical parts using a robotic arm.

Lane-Level Road Extraction from High-Resolution Optical Satellite Images

High-quality updates of road information play an important role in smart city planning, sustainable urban expansion, vehicle management, urban planning, traffic navigation, public health and other fields. However, due to interference from road geometry and texture noise, it is difficult to avoid the decline of automation while accurately extracting roads. Therefore, we propose a high-resolution optical satellite image lane-level road extraction method. First, from the perspective of template matching and considering road characteristics and relevant semantic relations, an adaptive correction model, an MLSOH (multi-scale line segment orientation histogram) descriptor, a sector descriptor, and a multiangle beamlet descriptor are proposed to solve the interference from geometry and texture noise in road template matching and tracking. Second, based on refined lane-level tracking, single-lane and double-lane road-tracking modes are designed to extract single-lane and double-lane roads, respectively. In this paper, Pleiades satellite and GF-2 images are selected to set up different scenarios for urban and rural areas. Experiments are carried out on the phenomena that restrict road extraction, such as tree occlusion, building shadow occlusion, road bending, and road boundary blurring. Compared with other methods, the proposed method not only ensures the accuracy of lane-level road extraction but also greatly improves the automation of road extraction.

Intensity Gradients Technique: Synergy with Velocity Gradients and Polarization Studies

Abstract Magnetic fields are ubiquitous in the interstellar medium but notoriously difficult to study through observation. Making use of the advances in our understanding of MHD turbulence and turbulent reconnection, the velocity gradients technique (VGT) was suggested and successfully applied to study magnetic fields utilizing spectroscopic data. Applying the tools developed for the VGT to intensity statistics, we introduce the intensity gradients technique (IGT) as a complementary tool that can be used synergistically with the VGT. In this paper, we apply the IGT to a diffuse H i region selected from the GALFA-H i survey and compare the intensity gradient (IG) maps with those obtained using velocity gradients, as well as Planck polarization measurements. We demonstrate the possibility of using the IGT and VGT for both studying the magnetic field and identifying shocks in the diffuse interstellar medium. We also explore the ability of the IGT in locating self-gravitating regions and calculating Alfvénic Mach numbers, both alone and in combination with the VGT and polarimetry. We compare the IGT with the histogram of relative orientation, which utilizes IGs to characterize the relative orientation of column density structures and local magnetic fields.

Content Based Image Retrieval for Community Retrieval from Given Nationality using an Efficient Combination Algorithm

There is tremendous requirement of such technique which can fulfill the entire requirement for retrieval of an image from available dataset which comes under computer vision. In this paper we discussed about the one of the application of CBIR using an efficient combination of two techniques. The application is retrieval of people images from database that comes under minority. In this paper we used an efficient combination of color image histogram technique and edge orientation histogram technique by dividing original image into small subblocks. The feature vector is formed by combination of two features obtained by above methodologies. The final features obtained by query image will be compared with the feature vector of database images using a new Canberra Distance classifier. Proposed method is designed for multiple self-prepared and some collected from internet databases. Our method includes the efficient integration of features such as color, texture, shape and orientation. The proposed method is compared with state of art techniques to prove the stable and highest accuracy of proposed work.

Features Combined Binary Descriptor Based on Voted Ring-Sampling Pattern

Most existing binary descriptors are only based on intensity and simply compare averaged intensities of one sample pair to obtain binary output. To address this issue, we propose a novel ring-sampling pattern based binary descriptor encoding both intensity and gradient. For intensity coding, a ring-sampling pattern is presented to define a number of sample points and their neighboring points given an interest point. The intensity difference between two sample points is obtained by performing the comparisons of the intensities of their corresponding neighboring points directly. Further, a majority based voting strategy is employed to obtain compact representation (1 bit or 3 bits) based on all these intensity difference among neighboring points. As for gradient coding, the gradient orientation histogram is computed for each sample point, and the gradient difference of two sample points is obtained by comparing the gradient magnitude on each orientation bin. The raw binary descriptor is constructed by concentrating the intensity and gradient differences of all the sample pairs, and two feature selection strategies are proposed to obtain the final compact descriptor, named as Features Combined Binary Descriptor based on Voted Ring-Sampling Pattern (BDVRP). The experimental results on the tasks of object recognition and image matching demonstrate the superiority and the effectiveness of the proposed descriptor, with comparison to the state-of-the-art hand-crafted binary descriptors.

Efficient Vehicle Detection and Distance Estimation Based on Aggregated Channel Features and Inverse Perspective Mapping from a Single Camera

In this paper a method for detecting and estimating the distance of a vehicle driving in front using a single black-box camera installed in a vehicle was proposed. In order to apply the proposed method to autonomous vehicles, it was required to reduce the throughput and speed-up the processing. To do this, the proposed method decomposed the input image into multiple-resolution images for real-time processing and then extracted the aggregated channel features (ACFs). The idea was to extract only the most important features from images at different resolutions symmetrically. A method of detecting an object and a method of estimating a vehicle’s distance from a bird’s eye view through inverse perspective mapping (IPM) were applied. In the proposed method, ACFs were used to generate the AdaBoost-based vehicle detector. The ACFs were extracted from the LUV color, edge gradient, and orientation (histograms of oriented gradients) of the input image. Subsequently, by applying IPM and transforming a 2D input image into 3D by generating an image projected in three dimensions, the distance between the detected vehicle and the autonomous vehicle was detected. The proposed method was applied in a real-world road environment and showed accurate results for vehicle detection and distance estimation in real-time processing. Thus, it was showed that our method is applicable to autonomous vehicles.

Histogram of Gradient Orientations of Signal Plots Applied to P300 Detection.

The analysis of Electroencephalographic (EEG) signals is of ulterior importance to aid in the diagnosis of mental disease and to increase our understanding of the brain. Traditionally, clinical EEG has been analyzed in terms of temporal waveforms, looking at rhythms in spontaneous activity, subjectively identifying troughs and peaks in Event-Related Potentials (ERP), or by studying graphoelements in pathological sleep stages. Additionally, the discipline of Brain Computer Interfaces (BCI) requires new methods to decode patterns from non-invasive EEG signals. This field is developing alternative communication pathways to transmit volitional information from the Central Nervous System. The technology could potentially enhance the quality of life of patients affected by neurodegenerative disorders and other mental illness. This work mimics what electroencephalographers have been doing clinically, visually inspecting, and categorizing phenomena within the EEG by the extraction of features from images of signal plots. These features are constructed based on the calculation of histograms of oriented gradients from pixels around the signal plot. It aims to provide a new objective framework to analyze, characterize and classify EEG signal waveforms. The feasibility of the method is outlined by detecting the P300, an ERP elicited by the oddball paradigm of rare events, and implementing an offline P300-based BCI Speller. The validity of the proposal is shown by offline processing a public dataset of Amyotrophic Lateral Sclerosis (ALS) patients and an own dataset of healthy subjects.

Gesture to Speech Conversion

Sign language is a primary mode of communication for people with language disabilities. This language uses a set of representation that is a sign of finger, expression or mixture of both to express their information among others. This system presents a new approach for translation based on mobile application of analysis of sign, recognition and generation of a textual description in Kannada language. We use two important steps of training and testing. In training, 50 different domains of video samples are collected, each domain contains 5 samples and assigns a class of words to each video sample and will be stored in the database. During the test, the sample is pre-processed using a median filter, a smart operator for edge detection, HOG (Histogram Oriented Gradients) is used for the extraction of features. SVM (Support Vector Machine) takes the input as a HOG feature and predicts the class label based on the trained SVM model. Finally, in the Kannada language, the text description will be produced. The average calculation time is minimal and with an acceptable recognition rate and validates the performance efficiency compared to the conventional model.

Fuzzy Histogram of Optical Flow Orientations for Micro-Expression Recognition

In high-stake situations, the micro-expressions reveal the hidden emotions of a person and it has potential applications in many areas. The recognition of such short-lived subtle expressions is a challenging task. The literature proposes several spatio-temporal features to encode the subtle changes on the face during a micro-expression. The spatial changes are almost indistinguishable as the facial appearance does not change appreciably. However, these changes possess a temporal pattern. This paper explores the temporal features associated with facial micro-movements and proposes fuzzy histogram of optical flow orientation (FHOFO) features for recognition of micro-expressions. The FHOFO constructs suitable angular histograms from optical flow vector orientations using histogram fuzzification to encode the temporal pattern for classifying the micro-expressions. We have also discussed the effect of inclusion and exclusion of the motion magnitudes during FHOFO feature extraction. It has been demonstrated by repeated experiments on the publicly available databases, that the performance of FHOFO is consistent and close or at times even better than the state-of-art techniques.

Establishing Pose Based Features Using Histograms for the Detection of Abnormal Infant Movements.

The pursuit of early diagnosis of cerebral palsy has been an active research area with some very promising results using tools such as the General Movements Assessment (GMA). In this paper, we conducted a pilot study on extracting important information from video sequences to classify the body movement into two categories, normal and abnormal, and compared the results provided by an independent expert reviewer based on GMA. We present two new pose-based features, Histograms of Joint Orientation 2D (HOJO2D) and Histograms of Joint Displacement 2D (HOJD2D), for the pose-based analysis and classification of infant body movement from video footage. We extract the 2D skeletal joint locations from 2D RGB images using Cao et al.'s method [1]. Using the MINI-RGBD dataset [2], we further segment the body into local regions to extract part specific features. As a result, the pose and the degree of displacement are represented by histograms of normalised data. To demonstrate the effectiveness of the proposed features, we trained several classifiers using combinations of HOJO2D and HOJD2D features and conducted a series of experiments to classify the body movement into categories. The classification algorithms used included k-Nearest Neighbour (kNN, k=1 and k=3), Linear Discriminant Analysis (LDA) and the Ensemble classifier. Encouraging results were attained, with high accuracy (91.67%) obtained using the Ensemble classifier.

High-dimensional image descriptor matching using highly parallel KD-tree construction and approximate nearest neighbor search

To overcome the high computational cost associated with the high-dimensional digital image descriptor matching, this paper presents a set of integrated parallel algorithms for the construction of K-dimensional tree (KD-tree) and P approximate nearest neighbor search (P-ANNS) on the modern massively parallel architectures (MPA). To improve the runtime performance of the P-ANNS, we propose an efficient sliding window for a parallel buffered P-ANNS on KD-tree to mitigate the high cost of global memory accesses. When applied to high dimensional real-world image descriptor datasets, the proposed KD-tree construction and the buffered P-ANNS algorithms are of comparable matching quality to the traditional sequential counterparts on CPU, while outperforming their serial CPU counterparts by speedup factors of up to 17and 163, respectively. The algorithms are also studied for the performance impact factors to obtain the optimal runtime configurations for various datasets. Moreover, we verify the features of the parallel algorithms on typical 3D image matching scenarios. With the classical local image descriptor signature of histograms of orientations (SHOT) datasets, the parallel KD-tree construction and image descriptor matching can achieve up to 11 and 138-fold speedups, respectively.