中文摘要：

随着视频监控应用的普及,超低分辨率人脸识别问题越来越突出。现存的人脸识别算法在面对超低分辨率人脸图像时无法给出满意识别性能。在一定程度上,人脸超分辨率方法可以提高人脸的分辨率,但是,目前主流的基于字典学习的人脸超分辨率方法并不能很好地处理超低分辨人脸图像重建问题,尤其是超分辨率人脸识别问题。利用人脸图像块的非局部相似性和多尺度相似性,提出一种改进的基于字典学习的超分辨率人脸重建算法,同时提出尺度不变特征的超低分辨率人脸识别方法。实验结果表明：本文提出的方法不但具有很好的视觉效果,而且还具有很好的识别效果,与目前主流的人脸超分辨率和识别算法相比具有明显的优势。

英文摘要：

The Very Low Resolution（VLR）problem happens in many face recognition application systems given the increasing demand for camera-based surveillance applications,.Currently,the existing face recognition algorithms cannot deliver satisfactory performance with VLR face images.While face super-resolution（SR）methods can be employed to enhance the resolution of the images,the existing dictionary learning-based face SR methods are inadequate for VLR face images.To overcome this problem,we propose a novel SR face reconstruction method based on non-local similarities and multiscale linear combinations and subsequently,a new approach for VLR face recognition based on resolution scale invariant features.Experimental results show that the proposed approach based on dictionary learning outperforms the existing algorithms in public face databases,obtaining agood visuality suitable for face recognition applications subject to the VLR problem.