计算机应用与软件2012，Vol.29Issue(4)：79-82,4.
基于HOG特征与子区域模糊融合的人耳识别研究
STUDY ON EAR RECOGNITION BY USING HISTOGRAM OF ORIENTED GRADIENT FEATURES AND SUB-REGION FUZZY FUSION
摘要
Abstract
As an emerging biometric identification technology, ear recognition has the unique advantages of its own. In this paper, a kind of novel ear recognition approach based on histogram of oriented gradient is studied by using the local feature information. An ear recognition scheme based on the combination of histogram of oriented gradient and sub-region fuzzy fusion is presented. The ear image is divided into a number of sub-regions, the features of histogram of oriented gradient in different sub-regions are extracted separately, and the fuzzy membership matching fusion strategy is introduced to obtain the final classification label. Comparative experiments with other methods indicate that the feature extraction method based on histogram of oriented gradient has higher recognition performance. Especially, 99. 75% recognition rate is obtained while testing on USTB ear image set 3.关键词
人耳识别/梯度方向直方图/子区域模糊融合/K近邻法Key words
Ear recognition/Histogram of oriented gradient/Sub-region fuzzy fusion/K nearest neighbours分类
信息技术与安全科学引用本文复制引用
封筠,梁晓霞,穆志纯..基于HOG特征与子区域模糊融合的人耳识别研究[J].计算机应用与软件,2012,29(4):79-82,4.基金项目
国家自然科学基金面上项目(60573058) （60573058）
河北省科技支撑计划重点项目(10213516D) （10213516D）
河北省自然科学基金项目(F2010001106). （F2010001106）
