Specularity Removal for Single Image Based on Inpainting and Blending with Parameter Estimation by Neural Networks over Multiple Feature Spaces

Abstract

Specularity removal is useful for image related applications that need consistent object surface appearance. For a single image it can be more challenging problem due to presence of different shapes, sizes and colors of specular regions, which may have some parts with totally missing data. The problem can become more difficult if the specular regions having partial information grow bigger, because the exact boundaries are difficult to mark. Any region filling method can provide unusual results because the appropriate boundaries selection is important for these methods. In this work, we address this problem and propose a scheme which can handle specular regions by segmenting both types of sub-regions of specularity. Our segmentation algorithm is multistage which uses Luminance as well as principal components for the identification of specular regions. For specularity removal, we proposed a three step scheme which includes balancing illumination, inpainting and blending. Finally feed-forward neural network is proposed to estimate the tunning parameters, which not only automate the whole process but also simplifies the difficult task of choosing parameters like size of specular regions or preprocessing selection. The results demonstrates the effectiveness of the proposed method for a variety of images having natural specular reflection.