中文摘要: 用基于非线性子空间的核独立成分分析方法 ( KICA) 对人脸图像进行特征提取, 用三层的 BP 网络作为分类器, 对人脸进行识别。在简单介绍基本的独立成分分析 ( ICA) 的基本原理的基础上, 对 KICA的原理和算法作了详细的描述, 并详细介绍了三层BP 网络的设计。最后为了验证 KICA+BP 网络的效果, 进行对比实验和分析。实验和分析的结果表明, 在人脸识别中, 该方法的效果明显好于其它方法。Abstr act : The Kernel Independent Component Analysis ( KICA) based on an entire function space of nonlinear subspace is usedfor feature extraction, and BP neural network is used as the classifier.First explains the basic concept of ICA in a concise way,then the KICA’ s basic principle and algorithm and how to construct the BP neural network is discussed, finally the experimentaland analysis results show that in the face recognition KICA+BP algorithm outperforms other algorithm.
展开▼
机译：中文摘要: 用基于非线性子空间的核独立成分分析方法 ( KICA) 对人脸图像进行特征提取, 用三层的 BP 网络作为分类器, 对人脸进行识别。在简单介绍基本的独立成分分析 ( ICA) 的基本原理的基础上, 对 KICA的原理和算法作了详细的描述, 并详细介绍了三层BP 网络的设计。最后为了验证 KICA+BP 网络的效果, 进行对比实验和分析。实验和分析的结果表明, 在人脸识别中, 该方法的效果明显好于其它方法。Abstr act : The Kernel Independent Component Analysis ( KICA) based on an entire function space of nonlinear subspace is usedfor feature extraction, and BP neural network is used as the classifier.First explains the basic concept of ICA in a concise way,then the KICA’ s basic principle and algorithm and how to construct the BP neural network is discussed, finally the experimentaland analysis results show that in the face recognition KICA+BP algorithm outperforms other algorithm.
展开▼
