CAJ | 학술논문

人脸识别是模式识别的一个重要分支，主要由特征提取和分类识别两个阶段决定，由于其小样本，高维数的特点，传统的分类器容易导致过学习问题，首先使用主成分分析法对人脸图像进行降维表示，然后将最小二乘支持向量机用于识别阶段，仿真实验显示的方法取得了较好的识别效果和识别效率。
인검식별시모식식별적일개중요분지，주요유특정제취화분류식별량개계단결정，유우기소양본，고유수적특점，전통적분류기용역도치과학습문제，수선사용주성분분석법대인검도상진행강유표시，연후장최소이승지지향량궤용우식별계단，방진실험현시적방법취득료교호적식별효과화식별효솔。
Face recognition is an important branch in pattern recognition , its effect is mainly decided by the two stages of feature extraction and classification method. Because of the small sample, high dimension, the traditional classifier can easily lead to overfitting problem,this paper uses principal component analysis to reduce the dimensionality of face image, then the least squares support vector machine is used for the recognition stage. The experimental results show that this method has good recognition effect and the recognition efficiency.