Abstract:

In the process of image acquisition in real face recognition system, there are always uncertain factors such as illumination, attitude and occlusion, and the recognition effect of traditional face recognition method is not good. Therefore, effectively handling these problems and improving recognition efficiency are still difficulty in part of face recognition systems. This article reviews the traditional methods of face recognition, focusing on the processing methods of face occlusion, this paper makes a detailed review from three aspects：how to reconstruct the generation model of occlusion image, how to detect the discrimination model of occlusion position and robust feature extraction, their advantages, disadvantages and application occasions are compared, the existing problems and future research directions of occluded face recognition are summarized.

Key words: occlusion face recognition, subspace regression, occlusion dictionary, robust error coding, feature extraction

摘要：

现实人脸识别系统的图像采集过程中往往存在光照、姿态、遮挡等不确定性因素，传统的人脸识别方法识别效果不佳，有效地处理这些问题提高识别效率仍是人脸识别系统中的难点。回顾了传统的人脸识别的相关方法，重点针对人脸遮挡的处理方法，从遮挡区域如何重构地生成模型，如何检测遮挡位置的判别模型及鲁棒特征提取三个方面进行了详细的综述，比较了各自的优缺点及应用场合，总结分析了目前有遮挡人脸识别存在的问题和未来研究方向。

关键词: 遮挡人脸识别, 子空间回归, 遮挡字典, 鲁棒误差编码, 特征提取