基于主成分分析和球结构支持向量机的人耳识别方法  

On an Ear Recognition Method Based on Principal Component Analysis and Sphere Support Vector Machine

作　　者：谌昌强[1] 肜丽[1] 

机构地区：[1]信阳农业高等专科学校计算机科学系,河南信阳464000

出　　处：《西南师范大学学报（自然科学版）》2013年第8期136-140,共5页Journal of Southwest China Normal University(Natural Science Edition)

摘　　要：提出一种基于主成分分析和球结构支持向量机的人耳识别方法.首先将人耳从侧面人脸中提取出来,然后采用主成分分析方法对人耳图像进行特征提取,最后采用球结构支持向量及对人耳图像进行训练和识别.与传统的多分类方法相比,该分类方法识别性能更高,这为非打扰式生物特征识别提供了一条有效途径.An ear recognition method has been proposed in this paper on the basis of principal component analysis and hyper-support vector machine.First an ear has been detected from an image of side face,and then the PCA method used to extract ear features,and,at last,the ear features have been trained and tested by means of sphere SVM.Comparing with other traditional multi-class SVMs,the proposed method achieved higher performance,thus,there comes a novel effective approach to the non-intrusive biometric recognition.

关 键 词：人耳识别 主成分分析 球结构支持向量机 多分类 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]