Detection and removal of shadow in still images using illumination invariant method

Abstract

Shadow detection and removal is fundamental problem in computer graphics and computer vision communities, which can greatly improve the performance of various applications, such as image interpretation and object classification. Shadow removal is also beneficial to increase the visual realism and physical realism in image editing and processing. As a preprocess procedure, we present an automatic shadow detection method to obtain accurate shadow boundaries. Then based on the shadow detection results, we develop an efficient shadow removal method using illumination invari ant method to produce high-quality shadow-free image. Experimental results show that it can accurately detect the shadow regions in an image. In some cases, intensity of shadow matches with that of dark objects and it founds difficulty to correctly detect the shadow region due to shadings present in the images that of dark intensity objects. The algorithm works well on natural scene images and easily removes the shadow regions in them.