This paper addresses the problem of recognizing and removing shadows from monochromatic natural images.Without chromatic information, shadow classification is very challenging because the invariant color cues are unavailable. Natural scenes make this problem even harder because of ambiguity from many near black objects. We propose to use both shadow-variant and shadow-invariant cues from illumination, textural and odd order derivative characteristics. Such features are used to train a classifier from boosting a decision tree and integrated into a Conditional random Field, which can enforce local consistency over pixel labels. The proposed approach is evaluated using both qualitative and quantitative results based on a novel database of hand-labeled shadows. Based on the classification results, our system automatically remove the shadows by assuming the illumination change model in the gradient domain is approximately a Gaussian. Our results show shadowed areas of an image can be identified using proposed monochromatic cues and the recovered shadow-free images are useful for mining missing content originally hidden in shadows.
|School of Electrical Engineering and Computer Science
University of Central Florida