Graphical Representation for Heterogeneous Face Recognition

Abstract

Abstract-Heterogeneous face recognition (HFR) refers to matching face images acquired from different sources (i.e., different sensors or different wavelengths) for identification. HFR plays an important role in both biometrics research and industry. In spite of promising progresses achieved in recent years, HFR is still a challenging problem due to the difficulty to represent two heterogeneous images in a homogeneous manner. Existing HFR methods either represent an image ignoring the spatial information, or rely on a transformation procedure which complicates the recognition task. Considering these problems, we propose a novel graphical representation based HFR method (G-HFR) in this paper. Markov networks are employed to represent heterogeneous image patches separately, which takes the spatial compatibility between neighboring image patches into consideration. A coupled representation similarity metric (CRSM) is designed to measure the similarity between obtained graphical representations. Extensive experiments conducted on multiple HFR scenarios (viewed sketch, forensic sketch, near infrared image, and thermal infrared image) show that the proposed method outperforms state-of-the-art methods.

Sparse graphical representation based discriminant analysis for heterogeneous face recognition

“…Accuracy Method Accuracy Fisherface [41] 28.82% OpenBR [46] 10.80% TFSPS [6] 72.62% MrFSPS [35] 75.36% PLS [17] 51.00% MvDA [19] 55.50% LRBP [24] 91.12% P-RS [3] 83.95% G-HFR [30] 96.04% SGR-DA 96.97%…”

“…In existing methods [5], [6], [30], K nearest related neighbors are selected from these related patches and the probe sketch patch y i can be regarded as a linear combination of the K nearest related neighbors weighted by a column vector w yi = (w yi,1 , · · · , w y i,K ) T . A Markov networks model can then be built by jointly modeling all probe sketch patches and their nearest neighbors:…”

“…Because there are 250 pairs in the representation dataset, the size of related neighbors M in our method is 250. To compare with existing methods [5], [6], [30] which manually selected K nearest neighbors, we set the number of nearest neighbors K to be 15,20,25,30,35,40 and the accuracies of different fixed number of related neighbors are shown in Fig. 4, denoted as "Fixed neighbors approach".…”

“…The forensic sketch database [30] contains 168 real-world forensic sketches with corresponding mug shot photos. Examples of forensic sketch and mug shot photos are shown in Fig.…”

Fast Preprocessing for Robust Face Sketch Synthesis

“…Exemplar-based face sketch synthesis has received much attention in recent years ranging from digital entertainment to law enforcement [Liu et al, 2007;Wang et al, 2014;Zhang et al, 2015b;Peng et al, 2016b;Peng et al, 2016a;Wang et al, 2017]. Typically these methods usually consist of two steps.…”