Intrinsic Face Image Decomposition from RGB Images with Depth Cues

Abstract

As a pre-step of reconstructing face attributes technology, the quality of face intrinsic image decomposition result has a direct impact on the sub-operations of reconstructing face attributes detail. There are two challenging problems with the intrinsic face image decomposition methods which are the quality of face-base intrinsic image, and the details of the shading image. In this study a new image model for intrinsic face image decomposition from RGB images with depth cues is proposed to produce high quality results even with simple constraints. The proposed model consists of three main steps: face cropping operation, processing the RGB color normalization, and the super-pixel segmentation. The face image is first cropped to get face area, then a color normalization process for the cropped face image is used to normalize RGB pixels, and finally the super-pixel segmentation based on mean shift algorithm is applied which has a good performance on reduce artifact and shading image’s detail retention. To evaluate the proposed model, both qualitative and quantitative assessments be used. The qualitative assessment is based on human subjective visual standards to compare the intrinsic images results, and the quantitative assessment is based on the data analyze of the image information entropy. Qualitative and quantitative results both demonstrate that the performance of the proposed model is better than other techniques in the field of intrinsic face image decomposition.