Periocular region-based person identification in the visible, infrared and hyperspectral imagery

Abstract

Face recognition performance degrades significantly under occlusions that occur intentionally or unintentionally due to head gear or hair style. In many incidents captured by surveillance videos, the offenders cover their faces leaving only the periocular region visible. We present an extensive study on periocular region based person identification in video. While, previous techniques have handpicked a single best frame from videos, we formulate, for the first time, periocular region based person identification in video as an image-set classification problem. For thorough analysis, we perform experiments on periocular regions extracted automatically from RGB videos, NIR videos and hyperspectral image cubes. Each image-set is represented by four heterogeneous feature types and classified with six state-of-the-art image-set classification algorithms. We propose a novel two stage inverse Error Weighted Fusion algorithm for feature and classifier score fusion. The proposed two stage fusion is superior to single stage fusion. Comprehensive experiments were performed on four standard datasets, MBGC NIR and visible spectrum [1], CMU Hyperspectral [2] and UBIPr [3]. We obtained average rank-1 recognition rates of 99.8, 98.5, 97.2, and 99.5% respectively which are significantly higher than the existing state of the art. Our results demonstrate the feasibility of image-set based periocular biometrics for real world applications.

A survey on periocular biometrics research

“…Table 2 summarizes existing research dealing with the task of locating the eye position directly, without relying on full-face or iris detectors. Uhl and Wild (2012) and Uzair et al (2015) used the VJ detector of face sub-parts. Uzair et al (2015) also experimented with the CMU hyperspectral database, which has images captured simultaneously at multiple wavelengths.…”

Current Advances in Hyperspectral Face Recognition

“…Hyperspectral imaging initially found its applications for aerial and remote sensing applications such as satellite imaging for earth observation [15] and astrophysical image application [16]. During the last few decades, due to the reduction in the hyperspectral camera cost and the increase in the imaging speed, hyperspectral imaging is finding new potential avenues in fields such as chemistry [17], agriculture [18], material classification [19], [20], forensic examination of document image analysis [21]- [23], and face recognition [24]- [27].…”

Survey of Periocular Recognition Techniques

“…This area of the face is easily captured with ease from the subject, for example by surveillance cameras. Thirdly, in crime scenes where masks hide the face or in cases where the subject's face is covered due to religious or cultural beliefs, the periocular region could still be captured providing useful details, that is, it is robust to face occlusion and is least affected by expression change [6].…”

“…However, traditional face recognition systems perform optimally for images captured under controlled conditions. Their performance degrades with images captured under challenging scenarios such as varying expression, pose, lightning conditions and occlusion [6].…”