Fast pose invariant face recognition using super coupled multiresolution Markov Random Fields on a GPU

• The merit of the daisy descriptor for face image representation is investigated.
• The complexity of MRF matching is addressed using the super coupling transform.
• An innovative GPU implementation of the multi resolution MRF matching is designed.
• The significant speed up achieved makes the MRF approach a practical proposition.
• State-of-the-art results are achieved on challenging databases for face recognition.

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.