Role of color in face recognition

Neural correlates of shape and surface reflectance information in individual faces

Faces are recognized by means of both shape and surface reflectance information. However, it is unclear how these two types of diagnostic information are represented in the human brain. To clarify this issue, we tested 14 participants in an event-related functional magnetic resonance adaptation paradigm, with four conditions created by using a 3D morphable model: (1) repetition of the same adapting face; (2) variation in shape only; (3) variation in surface reflectance only; (4) variation in both shape and surface reflectance. Change in face shape alone was the dominant driving force of the adaptation release in functionally defined face-sensitive areas in the right hemisphere (fusiform face area [FFA], occipital face area [OFA]). In contrast, homologous areas of the left hemisphere showed comparable adaptation release to changes in face shape and surface reflectance. When both changes in shape and reflectance were combined, there was no further increased release from adaptation in face-sensitive areas. Overall, these observations indicate that the two main sources of information in individual faces, shape and reflectance, contribute to individual face sensitivity found in the cortical face network. Moreover, the sensitivity to shape cues is more dominant in the right hemisphere, possibly reflecting a privileged mode of global (holistic) face processing.

Color face recognition for degraded face images

In many current face-recognition (FR) applications, such as video surveillance security and content annotation in a web environment, low-resolution faces are commonly encountered and negatively impact on reliable recognition performance. In particular, the recognition accuracy of current intensity-based FR systems can significantly drop off if the resolution of facial images is smaller than a certain level (e.g., less than 20 x 20 pixels). To cope with low-resolution faces, we demonstrate that facial color cue can significantly improve recognition performance compared with intensity-based features. The contribution of this paper is twofold. First, a new metric called "variation ratio gain" (VRG) is proposed to prove theoretically the significance of color effect on low-resolution faces within well-known subspace FR frameworks; VRG quantitatively characterizes how color features affect the recognition performance with respect to changes in face resolution. Second, we conduct extensive performance evaluation studies to show the effectiveness of color on low-resolution faces. In particular, more than 3000 color facial images of 341 subjects, which are collected from three standard face databases, are used to perform the comparative studies of color effect on face resolutions to be possibly confronted in real-world FR systems. The effectiveness of color on low-resolution faces has successfully been tested on three representative subspace FR methods, including the eigenfaces, the fisherfaces, and the Bayesian. Experimental results show that color features decrease the recognition error rate by at least an order of magnitude over intensity-driven features when low-resolution faces (25 x 25 pixels or less) are applied to three FR methods.