二维主元素分析(2DPCA)是基于二维图像,而不是像PCA一样基于一维的向量化图像,是一种用于人脸识别中的典型的特征提取技巧,与传统的PCA方法相比,它具有更高的识别率和更短的特征提取时间.运用2DPCA的手写体数字识别方法,与PCA方法在误识率上进行了数值对比试验.然后,在特征提取阶段进行改进,它是一个样本图像分组策略,称之为NetPCA,此方法比较好的综合了统计特征和结构特征两种提取方法.%Two-dimensional principal component analysis (2DPCA) is based on the 2D images rather than 1 D vectorized images like PCA,which is a classical feature extraction technique in face recognition.Compared with the traditional PCA,2DPCA has higher recognition rate and shorter feature extraction time.Using the 2DPCA method of handwritten digit recognition,and it has a contrast experiment with PCA in the error rate.Then,it improves in the feature extraction stage,it is a sample image group strategy,and it is called NetPCA,this method combines statistical characteristics and structure characteristics feature extraction methods.
展开▼