Mohammadzade Hoda, Sayyafan Amirhossein, Ghojogh Benyamin
J Opt Soc Am A Opt Image Sci Vis. 2018 Jul 1;35(7):1149-1159. doi: 10.1364/JOSAA.35.001149.
The variation of pose, illumination, and expression continues to make face recognition a challenging problem. As a pre-processing step in holistic approaches, faces are usually aligned by eyes. The proposed method tries to perform a pixel alignment rather than eye alignment by mapping the geometry of faces to a reference face while keeping their own textures. The proposed geometry alignment not only creates a meaningful correspondence among every pixel of all faces, but also removes expression and pose variations effectively. The geometry alignment is performed pixel-wise, i.e., every pixel of the face is corresponded to a pixel of the reference face. In the proposed method, the information of intensity and geometry of faces is separated properly, trained by separate classifiers, and finally fused together to recognize human faces. Experimental results show a great improvement using the proposed method in comparison to eye-aligned recognition. For instance, at the false acceptance rate (FAR) of 0.001, the recognition rates are respectively improved by 24% and 33% in the Yale and AT&T datasets. In the labeled faces in the wild dataset, which is a challenging, big dataset, improvement is 20% at a FAR of 0.1.
姿势、光照和表情的变化使得人脸识别仍然是一个具有挑战性的问题。作为整体方法中的预处理步骤，人脸通常通过眼睛进行对齐。所提出的方法试图通过将人脸的几何形状映射到参考人脸，同时保留其自身纹理，来执行像素对齐而非眼睛对齐。所提出的几何对齐不仅在所有脸的每个像素之间创建了有意义的对应关系，而且有效地消除了表情和姿势的变化。几何对齐是逐像素进行的，即人脸的每个像素都与参考人脸的一个像素对应。在所提出的方法中，人脸的强度和几何信息被适当分离，由单独的分类器进行训练，最后融合在一起以识别人脸。实验结果表明，与眼睛对齐识别相比，使用所提出的方法有很大的改进。例如，在误识率（FAR）为0.001时，在耶鲁和AT&T数据集中，识别率分别提高了24%和33%。在具有挑战性的大型野生标注人脸数据集中，当FAR为0.1时，识别率提高了20%。
