| 基于局部特征的部分遮挡人耳识别 |
| |
| 引用本文： | 袁立,穆志纯,曾慧.基于局部特征的部分遮挡人耳识别[J].北京科技大学学报,2010,32(4). |
| |
| 作者姓名： | 袁立 穆志纯 曾慧 |
| |
| 作者单位： | 北京科技大学信息工程学院,北京,100083 |
| |
| 基金项目： | 国家自然科学基金资助项目(No.60973064);;北京市教育委员会重点学科共建资助项目(No.XK100080537);;北京市自然科学基金资助项目(No.4102039) |
| |
| 摘 要： | 通过对人耳受到部分遮挡时识别的研究,提出了一种基于局部特征的部分遮挡人耳识别方法,即首先利用Gabor小波对人耳图像进行特征提取,由于该特征维数较高,再使用核Fisher判别分析(KFDA)方法进行有效降维后用于人耳识别.在逐步分析人耳各个子区域的鉴别能力的基础上,提出了基于分块图像和概率模型的识别方法.在北京科技大学(USTB)人耳图像库上的实验结果表明:基于Gabor滤波后图像所提取的特征比基于原始图像直接提取的特征具有更高的识别率,基于分块图像的识别率高于基于整体图像的识别率.
|
| 关 键 词： | 人耳识别 部分遮挡 Gabor特征 核Fisher判别分析 局部特征 |
Partially occluded ear recognition based on local features |
| |
| YUAN Li,MU Zhi-chun,ZENG Hui.Partially occluded ear recognition based on local features[J].Journal of University of Science and Technology Beijing,2010,32(4). |
| |
| Authors: | YUAN Li MU Zhi-chun ZENG Hui |
| |
| Abstract: | A local feature based approach was proposed for ear recognition under partial occlusion.Firstly,the Gabor filter is applied for feature extraction.Because the Gabor feature vector is of high dimension,kernel Fisher discriminant analysis(KFDA)is used for dimension reduction as well as class separability enhancement.Based on investigations on the different discriminating ability of sub-regions in ear images,a sub-region and probability based model is proposed for recognition.Experimental results on the USTB e... |
| |
| Keywords: | |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
