摘要
在人像识别方面,传统的特征提取方法大都是线性的,不能很好地保持样本的拓扑结构。支持向量机能提高学习的泛化能力,防止过学习,是一种很好的分类器。为此,提出一种增强的LLE(Locally Linear Em- bedding)和SVM(support Vector Machine)结合的人像识别方法,采用PCA(Principal Component Analysis)与LLE相结合算法,对光照归一化处理过的人脸图像进行特征提取,利用SVM的分类机制对人脸图像样本集进行训练和识别。在ORL(Olivetti Research Laboratory)人脸数据库上实验表明,该算法稳健、快速,识别率达到了90%以上。
For face recognition, most of the traditional methods which reduce the high dimensional data are linear. Support vector machine can enhance the generation ability of study, and can overcome the disadvantage of overfitting. The paper proposes a method for face recognition using the enhanced LLE (Locally Linear Embedding) and SVM (Support Vector Machine). After extracting the features of the pre-processing face images using PCA ( Principal Component Analysis) and LLE, we train the feature sets and recognize the faces with the classification methods of SVM. Experiment results on ORL (Olivetti Research Laboratory) database demonstrate that the algorithm is effective.
出处
《吉林大学学报(信息科学版)》
CAS
2008年第1期48-54,共7页
Journal of Jilin University(Information Science Edition)
基金
吉林省科技发展计划重点基金(20060330)
关键词
人脸识别
局部线性嵌入
主成分分析法
支持向量机
face recognition
locally linear embedding (LLE)
principal component analysis (PCA)
support vector machine (SVM)