Abstract
This paper proposes a new methodology to improve appearance-based thermal face recognition methods by using an enhanced representation of the thermal face information. This new representation is obtained by combining the pixels of the thermal face image and the vascular network information that is extracted from the same thermal face image. The effect of using the enhanced representation is evaluated for 5 different face recognition methods (LBP, WLD, GABOR, SIFT, SURF) in two public thermal face databases (Equinox and UCHThermalFace). The experimental results show that the proposed enhanced representation improves the performance of most of the analyzed appearance-based methods. The largest improvements are obtained when this representation is used together with methods based on the Gabor Jet Descriptor (GJD), the Weber Linear Discriminant (WLD) and Speeded Up Robust Features (SURF). In general terms the improvement is larger in indoor setups than in outdoors.
Acknowledgements
This research was partially funded by the FONDECYT-Chile Grants 11130466, 3120218 and 1130153.
Disclosure statement
No potential conflict of interest was reported by the authors.
Notes
1. In the following we will refer to “vascular network information”, “vascular network”, or “extracted vascular network” indistinctively, even if the obtained representation does not necessarily corresponds the exact vascular network or its topology. See (Pradeep Buddharaju et al., 2008) for an analysis on the extraction of vascular networks from thermal images
2. In all experiments on the UCHThermalFace DB the face images were first aligned using the annotated eyes’ position.
3. In these experiments the test and gallery images correspond to images taken in an indoor session or in an outdoor session. When the test images are indoor images, then the gallery images are outdoor-images, and vice versa. The outdoor images were captured in summer (with high temperatures up to 30 degrees Celsius), and at times the faces, as well as the camera, were receiving direct sunlight.