分组对梯度方向直方图表示方法的影响

2017 Fourth International Conference on Signal Processing, Communication and Networking (ICSCN) Pub Date : 2017-03-01 DOI:10.1109/ICSCN.2017.8085684

K. Karthikeyan, A. Karpagam, M. Manikandan

{"title":"分组对梯度方向直方图表示方法的影响","authors":"K. Karthikeyan, A. Karpagam, M. Manikandan","doi":"10.1109/ICSCN.2017.8085684","DOIUrl":null,"url":null,"abstract":"This paper focuses on comparing orientation binning to perform Histograms of Oriented Gradients algorithm for the feature extraction process. The HOG algorithm comprises of gradient computation, orientation binning and block normalization aimed towards object detection. Three angles of binning are considered for (3bins, 6bins, and 9bins) with angles.64×128 image sample is taken from INRIA Person Data set to extract the feature points, using which human detection can be enhanced. The HOG technique is observed through various orientation binning obtained from experimental simulation results on MATLAB.","PeriodicalId":383458,"journal":{"name":"2017 Fourth International Conference on Signal Processing, Communication and Networking (ICSCN)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Influence of binning in Histograms of Oriented Gradients method representation\",\"authors\":\"K. Karthikeyan, A. Karpagam, M. Manikandan\",\"doi\":\"10.1109/ICSCN.2017.8085684\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper focuses on comparing orientation binning to perform Histograms of Oriented Gradients algorithm for the feature extraction process. The HOG algorithm comprises of gradient computation, orientation binning and block normalization aimed towards object detection. Three angles of binning are considered for (3bins, 6bins, and 9bins) with angles.64×128 image sample is taken from INRIA Person Data set to extract the feature points, using which human detection can be enhanced. The HOG technique is observed through various orientation binning obtained from experimental simulation results on MATLAB.\",\"PeriodicalId\":383458,\"journal\":{\"name\":\"2017 Fourth International Conference on Signal Processing, Communication and Networking (ICSCN)\",\"volume\":\"44 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 Fourth International Conference on Signal Processing, Communication and Networking (ICSCN)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICSCN.2017.8085684\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 Fourth International Conference on Signal Processing, Communication and Networking (ICSCN)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSCN.2017.8085684","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

本文重点介绍了比较方向分形法来进行方向梯度直方图算法的特征提取过程。HOG算法包括梯度计算、方向分割和块归一化，以实现目标检测。对于有角度的(3bins, 6bins和9bins)，考虑了三个角度的装箱。从INRIA Person Data集中提取64×128图像样本，提取特征点，增强人体检测。通过MATLAB上的实验仿真结果得到的各种方向分束来观察HOG技术。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Influence of binning in Histograms of Oriented Gradients method representation

This paper focuses on comparing orientation binning to perform Histograms of Oriented Gradients algorithm for the feature extraction process. The HOG algorithm comprises of gradient computation, orientation binning and block normalization aimed towards object detection. Three angles of binning are considered for (3bins, 6bins, and 9bins) with angles.64×128 image sample is taken from INRIA Person Data set to extract the feature points, using which human detection can be enhanced. The HOG technique is observed through various orientation binning obtained from experimental simulation results on MATLAB.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2017 Fourth International Conference on Signal Processing, Communication and Networking (ICSCN)

自引率

0.00%

发文量