Histogram of oriented gradients

About: Histogram of oriented gradients is a research topic. Over the lifetime, 2037 publications have been published within this topic receiving 55881 citations. The topic is also known as: HOG.

DFOB: Detecting and describing features by octagon filter bank for fast image matching

Abstract: Feature correspondence is vital in image processing and computer vision. To find corresponding pairs efficiently, in this paper it is proposed that feature detector and descriptor are constructed from the same octagon filter bank (DFOB). The DFOB method is a novel method for the detection, orientation computation, and description of feature points, and is very efficient as computationally implemented by integral images. The matching capability of DFOB is close to the prevalent methods such as SIFT and SURF, because they all detect blob-like image structures as interest features and describe these features using histogram of oriented gradients. Experimental results on benchmark datasets demonstrate that the matching performance of DFOB is comparable with the SIFT and SURF algorithms, while the computational cost is much lower, especially the proposed descriptor is about 50 times faster than SURF descriptor.

Leaf Identification Using HOG, KNN, and Neural Networks

Abstract: The main objective of this paper is to identify the leaves using the concepts of image processing. A dataset comprising 1900 images of 18 leaf species has been used to train our machine. Three major steps—image preprocessing, feature extraction (using Histogram of Oriented Gradients (HOG)) and classification—have been performed. The initial step includes grayscale conversion and represents the input image as a zero-one matrix. In the next step, 900 features have been extracted using HOG. The last step comprises classification of two supervised learning methodologies—K-nearest neighbors and backward propagation algorithm using artificial neural networks. Performance of the two methods has been compared, and artificial neural networks have proved to be a better choice with an approximate accuracy of 97%. The implementation has been carried out using MATLAB and its toolboxes.

An Approach for Secure Identification and Authentication for Biometrics using Iris

Abstract: One of the most accurate biometric authentication methods is iris pattern recognition. Basically iris recognition is a method of biometric recognition and authentication that uses recognition strategies on images of a people eyes. This paper presents a secure authentication using iris recognition system. A usual recognition system has distinctive phases like enrollment phase and authentication phase. In this proposed work CASIA V4 iris is considered as a database. The flow of work starts with pre-processing, feature extraction and classification. This procedure is implemented using evaluation of various iris pattern recognition features by using Histogram of Oriented Gradients (HOG), Gray Level Co-occurrence Matrix (GLCM), Hausdroff Dimensions (HD), Biometric Graph Matching (BGM) and 2D - Gabor filter techniques. Then, a State Vector Machine (SVM), Weighted Euclidian Distance (WED) and Jaccard coefficient and Dice coefficient classifier is used to verify and authenticate the patterns. Accordingly, SVM is regarded as most distinctive and most efficient technique for the proposed iris identification and authentication system.

Human Identification Using Periocular Biometrics

Abstract:  Abstract—Biometrics provides a secure method of authentication and identification. Biometric data are difficult to replicate and steal. Unique identifiers include fingerprints, hand geometry, earlobe geometry, retina and iris patterns, voice waves, DNA, and signatures. This paper is based on Periocular biometric recognition, which is the appearance of the region around the eye. Periocular recognition may be useful in applications where it is difficult to obtain a clear picture of an iris for iris biometrics or a complete picture of a face for face biometrics. Acquisition of the Periocular biometrics does not require high user cooperation and close capture distance. This region usually encompasses the eyelids, eyelashes, eyebrows, and the neighbouring skin area. Periocular biometrics encompasses the information of face recognition and iris recognition system. In this paper, the Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOGs) are used for the feature extraction on the Periocular images. LBP is a type of feature used for classification in computer vision and a powerful feature for texture. HOGs are used for the purpose of object detection using gradient features. For an effective classification and recognition of an authorized individual Back propagation neural network (BPNN) classifier is used.

High Dimensional Abnormal Human Activity Recognition Using Histogram Oriented Gradients and Zernike Moments

Abstract: In this paper a robust abnormal human activity recognition framework is proposed which goals to recognize any unusual activity to the elderly people and to strengthen the concept of independent and quality living. The framework is structured to construct a robust feature vector by computing integrated feature vector: Histogram of Oriented Gradients (HOG) and Zernike moments on Average Energy Images (AEI). Formation of AEI images provides a compact representation of the video sequences without any Spatio-temporal loss of information. Integration of HOG and Zernike moments augments inter-class separation and translational and rotational invariance. The depth silhouettes are acquired by Microsoft's Kinect sensor which are used to generate clean binary silhouettes by background subtraction making the pre-processing faster and simpler with accuracy. The combined feature vector dimensions are reduced by applying PCA and SVM is applied to classify the activities. The proposed work is validated on publically available UR fall detection and Kinect Activity Recognition Dataset (KARD) 3D dataset. The experiments exhibit impressive results with The average recognition accuracy achieved on these datasets are 94% and 95.22% ARA for UR fall dataset, and KARD dataset, respectively