PALMPRINT RECOGNITION BASED ON MODIFIED DCT FEATURES AND RBF NEURAL NETWORK

摘要：

In this paper, a novel palmprint recognition approach is presented. A modified Discrete Cosine Transform based feature extraction method is used to obtain palmprint features. Furthermore, a Radial Basis Function Neural Network is employed for palmprint classification. In order to facilitate the training of Radial Basis Function Neural Network, Principal Components Analysis is applied to reduce these features to a reasonable dimension. The experiment results show that the method is effective.

关键词： Biometrics Palmprint recognition RBF neural network DCT-mod2 PCA

作者: PENG-FEI YU DAN XU

作者单位: School of Information, Yunnan University, Kunming 650091, China

会议类型: 国际会议

会议名称: 2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

会议地点: 昆明

会议语种:英文

页码: 2982-2986

在线出版日期: 2008-07-12（万方平台首次上网日期，不代表论文的发表时间）