scispace - formally typeset
Search or ask a question
Topic

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.


Papers
More filters
Book ChapterDOI
18 Nov 2016
TL;DR: This work proposes a system for writer’s gender classification that is based on local textural and gradient features, which are successful in various pattern recognition applications.
Abstract: The gender identification in handwritten documents becomes to gain importance for various writer authentication purposes. It provides information for anonymous documents for which we need to know if they were written by a Man or a Woman. In this work, we propose a system for writer’s gender classification that is based on local textural and gradient features. Especially our proposed features are Histogram of Oriented Gradients (HOG) and Local Binary Patterns (LBP), which are successful in various pattern recognition applications. The classification step is achieved by SVM classifier. The results obtained on samples extracted from IAM dataset showed that the proposed features provide quite promising results.

11 citations

Journal ArticleDOI
TL;DR: RIHOG overcomes a disadvantage of the histogram of oriented gradients (HOG), which is very sensitive to image rotation, and uses the accumulated relative magnitude values of corresponding relative orientation calculated with neighboring pixels, which has an effect on reducing the sensitivity of image rotation.
Abstract: In this paper, we propose a new image descriptor, that is, a rotation invariant histogram of oriented gradients (RIHOG). RIHOG overcomes a disadvantage of the histogram of oriented gradients (HOG), which is very sensitive to image rotation. The HOG only uses magnitude values of a pixel without considering neighboring pixels. The RIHOG uses the accumulated relative magnitude values of corresponding relative orientation calculated with neighboring pixels, which has an effect on reducing the sensitivity to image rotation. The performance of RIHOG is verified via the index of classification and classification of Brodatz texture data.

11 citations

Proceedings ArticleDOI
01 Jan 2015
TL;DR: The proposed Depth Weighted Histogram of Oriented Gradients (DWHOG) feature calculated from RGB and depth images can estimate human orientation robustly to complex backgrounds, compared to a method using conventional HOG features.
Abstract: Estimation of human orientation contributes to improving the accuracy of human behavior recognition. However, estimation of human orientation is a challenging task because of the variable appearance of the human body. The wide variety of poses, sizes and clothes combined with a complicated background degrades the estimation accuracy. Therefore, we propose a method for estimating human orientation using coaxial RGBDepth images. This paper proposes Depth Weighted Histogram of Oriented Gradients (DWHOG) feature calculated from RGB and depth images. By using a depth image, the outline of a human body and the texture of a background can be easily distinguished. In the proposed method, a region having a large depth gradient is given a large weight. Therefore, features at the outline of the human body are enhanced, allowing robust estimation even with complex backgrounds. In order to combine RGB and depth images, we utilize a newly available single-chip RGB-ToF camera, which can capture both RGB and depth images taken along the same optical axis. We experimentally confirmed that the proposed method can estimate human orientation robustly to complex backgrounds, compared to a method using conventional HOG features.

11 citations

Journal ArticleDOI
24 Jun 2020-Sensors
TL;DR: Experimental results show that the proposed method achieves a high level of accuracy as well as low processing time when compared to existing methods, indicating that it is suitable for real-time applications.
Abstract: Automatic vehicle license plate recognition is an essential part of intelligent vehicle access control and monitoring systems With the increasing number of vehicles, it is important that an effective real-time system for automated license plate recognition is developed Computer vision techniques are typically used for this task However, it remains a challenging problem, as both high accuracy and low processing time are required in such a system Here, we propose a method for license plate recognition that seeks to find a balance between these two requirements The proposed method consists of two stages: detection and recognition In the detection stage, the image is processed so that a region of interest is identified In the recognition stage, features are extracted from the region of interest using the histogram of oriented gradients method These features are then used to train an artificial neural network to identify characters in the license plate Experimental results show that the proposed method achieves a high level of accuracy as well as low processing time when compared to existing methods, indicating that it is suitable for real-time applications

11 citations

Proceedings ArticleDOI
23 Apr 2013
TL;DR: This paper discusses the design and processor implementation of a system that detects and recognizes traffic signs present in an image and achieved recognition and classification accuracies of upto 90%.
Abstract: This paper discusses the design and processor implementation of a system that detects and recognizes traffic signs present in an image. Morphological operators, segmentation and contour detection are used for isolating the Regions of Interest (ROIs) from the input image, while five methods - Hu moment matching, histogram based matching, Histogram of Gradients based matching, Euclidean distance based matching and template matching are used for recognizing the traffic sign in the ROI. A classification system based on the shape of the sign is adopted. The performance of the various recognition methods is evaluated by comparing the number of clock cycles used to run the algorithm on the Texas Instruments TMS320C6748 processor. The use of multiple methods for recognizing the traffic signs allows for customization based on the performance of the methods for different datasets. The experiments show that the developed system is robust and well-suited for real-time applications and achieved recognition and classification accuracies of upto 90%.

11 citations


Network Information
Related Topics (5)
Feature extraction
111.8K papers, 2.1M citations
89% related
Convolutional neural network
74.7K papers, 2M citations
87% related
Deep learning
79.8K papers, 2.1M citations
87% related
Image segmentation
79.6K papers, 1.8M citations
87% related
Feature (computer vision)
128.2K papers, 1.7M citations
86% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202356
2022181
2021116
2020189
2019179
2018240