提出了一种基于图像分块的二维保局投影(分块2dlpp)的人脸识别方法。
A method of Two-Dimensional Locality Preserving Projections (2dlpp) for face recognition was proposed, based on modular image.
在仔细分析证件照片中人脸特点的基础上，提出了一种把人脸的几何特征矢量匹配和人脸的分块加权匹配相结合的思想。
Based on the analysis of human face in ID card, this paper proposes a new face recognition method, which integrates the geometric eigenvector matching with the weighted face subdivision matching.
当图像中的人脸是倾斜的情况时，我们可以利用分块积分投影，因此也适用于脸部旋转的情况。
When the face in image is obliqueness, we may use blocks gray projection. So the method could process rotated images. The method is simple and its calculation is less.
应用推荐