基于仿生模式识别与传统模式识别的人脸识别效果比较研究

Face Recognition:Biomimetic Pattern Recognition vs.Traditional Pattern Recognition

本文实现了一种基于仿生模式识别的人脸识别系统 ,并将其识别效果同最近邻分类器与不同核函数的SVM进行了分析比较 .以ORL人脸库为识别对象 ,针对有“拒识”的情况下 ,通过改变不同识别算法的可调参数 ,在保证参与训练人的正确识别率在大致相同水平的条件下 ,分析了参与训练人的错误识别率 (错识别为参与训练的其他人 )与未参与训练人的错误接受率 (错识别为参与训练的某人 )的优劣 .比较结果表明 。

Based on a new theory model-BPR (Biomimetic Pattern Recognition), a face recognition system is implemented. In order to compare the recognition performance of it with that of some TPR (traditional pattern recognition), such as NN-based method and SVM-based methods with different types of kernel functions, using the ORL face database, we analyze the misclassification rate and false acceptance rate at the same level of the correct recognition rate by adjusting parameters of different algorithms. Comparison results show that our method is superior to the other two methods.