A face image recognition scheme with strong tolerances to lighting fluctuations

In this paper, we propose a face recognition scheme that has strong tolerances to changes in the lighting environment. The current spread of cellular phones with camera devices has made biometric certification of face images possible, without adding extra devices. However, face images taken via cellular phones are fluctuated by lighting environments, because cellular phones are used both indoors and outdoors without limit. Therefore, the most serious problem is that lighting fluctuations decrease its recognition accuracy. Our proposed scheme is very simple. This scheme uses the lighting canonical space and creates a virtual subspace that contains various elements of lighting, without actually taking many face images under different environments. Simulation results show the proposed scheme can achieve not only a lower equal-error-rate of verification, but also higher precision of identification than the conventional subspace scheme.