摘要： 采用小波分解将原始图像分解为4幅子图像，分别对子图像利用HMM进行学习、识别，根据信息融合的方法确定最后的分类结果，同时改进了Samaria算法中直接利用原始图像灰度数据作为观察矢量，通过K－L变换将降维以后的特征矢量作为观察矢量。

关键词: 隐马尔可夫模型, 人脸识别, 小波分析, K-L变换

Abstract: A new approach is proposed in this paper, Dauechies orthogonal wavelet transform is used to preprocess the original face image, resulting in its four sub-images belonging to different frequency bands, and the sub-images are used to learn and recognize with HMM. An algorithm is designed to combine the multiple sort results, and the Karhunen Loeve (K-L) transform is used to extract a set of observations to improve the method by Asmaria.

中图分类号: 

• TP391.41