Color Space for Face Authentication Using Enhanced Fisher linear discriminant Model (EFM)

The performance of face authentication systems has steadily improved over the last few years, mainly focusing on models rather than on feature processing. State-of-the-art methods often use the grayscale face image as input. In this paper, we propose to use the color information as a feature for face image. The proposed feature set is tested on a benchmark database, namely XM2VTS, using Enhanced Fisher linear discriminant Model (EFM). Results show that the color information improves the performance and that the proposed model achieves robust state-of-the-art results.