一种基于人脸分割的人脸识别方法

A Facial Recognition Method Based on Face Segmentation

为了减少数据存储量,加快计算速度,提出一种人脸探测、识别方法。在复杂背景中提取到人脸部分图像并把包含人脸最主要的特征左右眼、鼻子、嘴巴、下巴从图像中单独提取出来,而丢弃人脸其他特征不明显部位,从而大大降低了图像矩阵的维数。在识别中应用PCA(主成分分析)法提取特征然后应用SVM(支持向量机)方法进行分类识别。根据ORL标准人脸库的实验表明,所提出的人脸识别方法具有较好的识别效果。

In order to reduce the amount of data storage and Speed up the calculation,this paper puts forward a method of face detection and recognition in a complex environment to extract the face part of the image and the face of the main character around eyes,forehead,nose,chin,separately extracted from the human face image,and cast it away face other characteristics is not obvious.Thus the dimension of the image matrix is greatly reduced.