中文摘要：

人脸图像信息中鼻子区域受表情、胖瘦、发型等变化的影响极小，为人脸识别过程提供了稳定的个体特征。首先对鼻子的生理结构进行了剖析，分析了利用鼻子区域识别个体的可行性及其特点，然后对提取鼻子特征的 Gabor 参数进行了简化，进一步用 Gabor 核 Fisher 判别分析算法在不同数据库上对鼻子区域的识别效果进行了实验分析。实验结果表明，在表情和姿态变化较大的情况下，鼻子区域的识别效果要比人脸的识别效果好。最后指出了下一步需要研究的关键问题。

英文摘要：

The nose area of a face can provide some stable individual characteristic information for personal recognition because of its tiny changes affected by expression,weight and hairstyle.The paper first dissects the physiological structure of the nose and discusses the feasibility and characteristics of nose recognition. Furthermore,authors simplify Gabor’s parameters in extracting nose features,and compare the recognition effect by experiment with the Gabor Kernel Fisher Discriminant Analysis in different databases.Experiment shows that the nose area has a better recognition result than the face when the face image has a rich expression or wide range poses.