Department of Computer Science, Hong Kong Baptist University, Kowloon, Hong Kong.
IEEE Trans Image Process. 2012 Jan;21(1):327-40. doi: 10.1109/TIP.2011.2162423. Epub 2011 Jul 18.
This paper addresses the very low resolution (VLR) problem in face recognition in which the resolution of the face image to be recognized is lower than 16 × 16. With the increasing demand of surveillance camera-based applications, the VLR problem happens in many face application systems. Existing face recognition algorithms are not able to give satisfactory performance on the VLR face image. While face super-resolution (SR) methods can be employed to enhance the resolution of the images, the existing learning-based face SR methods do not perform well on such a VLR face image. To overcome this problem, this paper proposes a novel approach to learn the relationship between the high-resolution image space and the VLR image space for face SR. Based on this new approach, two constraints, namely, new data and discriminative constraints, are designed for good visuality and face recognition applications under the VLR problem, respectively. Experimental results show that the proposed SR algorithm based on relationship learning outperforms the existing algorithms in public face databases.
本文针对人脸识别中的极低分辨率（VLR）问题进行了研究，在该问题中，待识别的人脸图像的分辨率低于 16×16。随着基于监控摄像机的应用需求的增加，VLR 问题在许多人脸应用系统中都会出现。现有的人脸识别算法在 VLR 人脸图像上的性能并不令人满意。虽然可以使用人脸超分辨率（SR）方法来提高图像的分辨率，但现有的基于学习的人脸 SR 方法在处理这种 VLR 人脸图像时效果不佳。为了解决这个问题，本文提出了一种新的方法，用于学习人脸 SR 中高分辨率图像空间和 VLR 图像空间之间的关系。基于这种新方法，分别为 VLR 问题下的良好视觉效果和人脸识别应用设计了两个约束条件，即新数据和判别约束条件。实验结果表明，基于关系学习的提出的 SR 算法在公共人脸数据库上优于现有的算法。
