期刊
PATTERN RECOGNITION LETTERS
卷 48, 期 -, 页码 49-59出版社
ELSEVIER
DOI: 10.1016/j.patrec.2014.05.017
关键词
Multiresolution MRFs; Renormalisation group transform; Super coupling transform; Image matching; Unconstrained-pose face recognition
资金
- EPSRC [EP/K014307/1, EP/H049665/1, EP/F069421/1]
- EPSRC [EP/F069421/1, EP/H049665/1, EP/K014307/1] Funding Source: UKRI
- Engineering and Physical Sciences Research Council [EP/K014307/1, EP/H049665/1, EP/F069421/1] Funding Source: researchfish
We discuss the problem of pose invariant face recognition using a Markov Random Field (MRF) model. MRF image to image matching has been shown to be very promising in earlier studies (Arashloo and Kittler, 2011) [4]. Its demanding computational complexity has been addressed in Arashloo et al. (2011) [6] by means of multiresolution MRFs linked by the super coupling transform advocated by Petrou et al. (1998) [37, 11]. In this paper, we benefit from the daisy descriptor for face image representation in image matching. Most importantly, we design an innovative GPU implementation of the proposed multiresolution MRF matching process. The significant speed up achieved (factor of 25) has multiple benefits: It makes the MRF approach a practical proposition. It facilitates extensive empirical optimisation and evaluation studies. The latter conducted on benchmarking databases, including the challenging labelled faces in the wild (LFW) database show the outstanding potential of the proposed method, which consistently achieves state-of-the-art performance in standard benchmarking tests. The experimental studies also show that the super coupled multiresolution MRFs deliver a computational speed up by a factor of 5 over and above the speed up achieved using the GPU implementation. (C) 2014 Elsevier B. V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据