【摘要】 提出了一种基于隐马尔可夫模型 (HMM)的人脸图像识别方法。对归一化的人脸图像 ,该方法 2D DCT变换域提取人脸图像的一维特征矢量。通过对HMM的训练和识别实验表明 ,文中提出的方法计算量少 ,运行速度较快 ,是一种比较适合工程应用的人脸识别算法。更多还原

【Abstract】 A human face recognition algorithm based on the Hidden Markov Model (HMM) is presented For normalized face image,the algorithm extracts onedimensional human face feature vectors in 2DDCT.The training and recognition results show that the method proposed reduces the computational complexity significantly and runs faster,it is a more effective algorithm for human face recognition in engineering application更多还原