Recovering variations in facial albedo from low resolution images. (February 2018)

• Record Type: Journal Article
• Authors: Chen, Xu; Zhang, Zhihong; Wang, Beizhan; Hu, Guosheng; Hancock, Edwin R.
• Is Part Of: Pattern recognition. Volume 74(2018:Feb.)
• Page Start: 373
• Page End: 384
• Publication Date: 2018-02
• Subjects: Facial albedo estimation -- Low quality facial image -- Sparse coding -- ADMM; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2017.09.019
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We propose a face image enhancement framework which can jointly estimate facial albedo and perform face super-resolution. It is more effective to simultaneously solve these two tasks, which both aim to recover the facial albedo or texture from low quality images. The proposed framework can be modeled as a non-convex optimization problem. We propose an efficient alternating optimization strategy which interleaves removing intrinsic facial variations and performing super resolution. Existing albedo estimation methods can only deal with single sources of intrinsic facial image variation, such as illumination variation. In contrast, our framework can model more diverse sources of facial image variation. Experiments demonstrate that the proposed method can also significantly improve the performance of face recognition and clustering when given very low resolution images with various facial variations. Abstract: Recovering facial albedo from low quality face images is a challenging task which arises when face recognition is attempted in the wild. Low quality of facial images is usually caused by extrinsic factors such as low resolution and noises, and intrinsic ones such as expressions. Existing research recovers facial albedo by dealing with the extrinsic and intrinsic factors separately. However, it is more natural and potentially more useful to approach albedo recovery by removing the two effects simultaneously. In this paper, we present a novel framework which can recover facial albedo by jointly solving these for both the extrinsic and intrinsic sources of uncertainty. This framework models albedo recovery problem by a joint optimization process which alternatively (1) removes intra-personal variations and (2) performs super resolution. To deal with the intrinsic sources of albedo variability, we use a linear model. To handle extrinsic problems associated with low quality imaging, we use a sparse coding method which is applied to super resolution. The proposed method can also significantly improve the performance of face recognition and clustering in case of very low resolution and in the presence of various facial variations. Extensive experiments and comparisons are conducted on the AR and FERET face databases. Experimental results show the effectiveness of the proposed method.