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.

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.

Offline Signature Verification and Forgery Detection Approach

Abstract: Signature verification and forgery detection is a challenging field with a lot of critical issues. Signatures forgery drives cooperates and business organizations to huge financial loss and also affects their security reputation. Highly accurate automatic systems are needed in order to prevent this kind of crimes. This paper introduce an automatic off-line system for signature verification and forgery detection. Different features were extracted and their effect on system recognition ability was reported. The computed features include run length distributions, slant distribution, entropy, Histogram of Gradients features (HoG) and Geometric features. Finally, different machine learning techniques were applied on the computed features: bagging tree, random forest and Support Vector Machine (SVM). it was noticed that SVM outperforms the other classifiers when applied on HoG features. The system was applied on Persian Offline Signature Data-set (UTSig) database and achieved satisfactory results in differentiating between genuine and forged signature.

Neonatal Facial Pain Assessment Combining Hand-Crafted and Deep Features

Abstract: In this paper we evaluate the combination of hand-crafted and deep learning-based features for neonatal pain assessment. To this end we consider two hand-crafted descriptors, i.e. Local Binary Patterns (LBP) and Histogram of Oriented Gradients (HOG), and features extracted from two pre-trained Convolutional Neural Networks (CNNs). Experimental results on the publicly available Infant Classification Of Pain Expressions (COPE) database show competitive results compared to previous methods.

Periocular recognition in cross-spectral scenario

Abstract: Periocular recognition has been an active area of research in the past few years. In spite of the advancements made in this area, the cross-spectral matching of visible (VIS) and near-infrared (NIR) periocular images remains a challenge. In this paper, we propose a method based on illumination normalization of VIS and NIR periocular images. Specifically, the approach involves normalizing the images using the difference of Gaussian (DoG) filtering, followed by the computation of a descriptor that captures structural details in the illumination normalized images using histogram of oriented gradients (HOG). Finally, the feature vectors corresponding to the query and the enrolled image are compared using the cosine similarity metric to generate a matching score. Performance of our algorithm has been evaluated on three publicly available benchmark databases of cross-spectral periocular images. Our approach yields significant improvement in performance over the existing approach.

Augmented reality three-dimensional object visualization and recognition with axially distributed sensing.

Abstract: An augmented reality (AR) smartglass display combines real-world scenes with digital information enabling the rapid growth of AR-based applications. We present an augmented reality-based approach for three-dimensional (3D) optical visualization and object recognition using axially distributed sensing (ADS). For object recognition, the 3D scene is reconstructed, and feature extraction is performed by calculating the histogram of oriented gradients (HOG) of a sliding window. A support vector machine (SVM) is then used for classification. Once an object has been identified, the 3D reconstructed scene with the detected object is optically displayed in the smartglasses allowing the user to see the object, remove partial occlusions of the object, and provide critical information about the object such as 3D coordinates, which are not possible with conventional AR devices. To the best of our knowledge, this is the first report on combining axially distributed sensing with 3D object visualization and recognition for applications to augmented reality. The proposed approach can have benefits for many applications, including medical, military, transportation, and manufacturing.