Illumination preprocessing for face images based on empirical mode decomposition

• The Logarithmic Empirical Mode Decomposition (EMD) algorithm is proposed to obtain an illumination-insensitive facial representation.
• An EMD based preprocessing method is proposed to reduce the effect of shadows on face images.
• Existing methods for restoring the frontal-illuminated face images are enhanced.

The Empirical Mode Decomposition (EMD) can adaptively decompose a complex signal into Intrinsic Mode Functions (IMFs) that are relevant to intrinsic physical significances, therefore is a powerful tool for multi-scale analysis of non-stationary signals. Towards restoring a frontal-illuminated face from a single image, in this paper we study the usage of EMD for manipulating the illumination issue on face images. We propose an EMD-based algorithm to extract the illumination-insensitive facial features. We also come up with an EMD-based scheme to detect the shadows and to reduce the effects of shadows on face images. By preserving the intrinsic facial features as well as lessening the shadows, it is more likely to restore the frontal-illuminated face image with good visual quality from a single image. Experiments verify the effectiveness of the proposed methods.