摘要
提出一种用于人脸识别的 E- HMM/ ANN混合网络 .该混合网络用 E- HMM的参数来表示人脸特征 ;用 E-HMM的输出似然值序列组成 ANN的输入矢量 ;用 ANN的鉴别训练能力来克服 E- HMM的基于最大似然准则训练算法区分力较差的弱点 ;同时利用 ANN的学习能力来提高 E- HMM的识别性能 .采用 ORL人脸库对混合网络进行识别实验 ,结果表明所提出的混合网络提高了人脸识别精度 .
Embedded- hidden Markov model (E-HMM) and artificial neural network (ANN) was combined within the hybrid architecture for face recognition. E-HMM was used to parameterize the face image. Every person' face was represented by a E-HMM, the output of likelihood of the E-HMM was encoded to form the input vector sending to ANN. By taking advantage of the discriminative training of ANN, the weakness in discrimination ability of the Maximum Likelihood training of E-HMM could be overcome, and the recognition performance was enhanced by means of the learning ability of ANN. Experiments with ORL(Olivetti Research Ltd.) face image database show that the discriminative ability and recognition performance of the hybrid architecture is better than normal E-HMM.
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2002年第11期1070-1073,共4页
Journal of Computer-Aided Design & Computer Graphics
