With varying illumination conditions, facial features obtained from images are distorted nonlinearly by variant lighting intensity and direction, so face recognition becomes very difficult. According to the "common assumption", illumination varies slowly and the face intrinsic feature (including 3D surface and reflectance) varies rapidly in local area, we can then consider high frequency features that represent the face intrinsic structure. FABEMD8 (Fast and Adaptive Bidimensional Empirical Mode Decomposition) is a fast and adaptive method of BEMD22 (Bidimensional Empirical Mode Decomposition), and not using time-consuming plane interpolation computation, it can decompose the image into multilayer high frequency images representing detail features and low frequency images representing analogy features. But we cannot make a quantitative analysis of how many detail features can be used to eliminate illumination variation. So we propose two measures to quantify the detail features, and with these measure weights, we can activitate FABEMD based multilayer detail images matching for face recognition under varying illumination. With PCA, the experiments based on Yale face database B and MU PIE face database show that the method proposed in this paper can get remarkable performance.
Extraction of Illumination-Invariant Features in Face Recognition by Empirical Mode Decomposition
