Object recognition with incomplete features based on evidence accumulation

In this paper, we address the problem of object recognition in clutter with incomplete features, focusing on challenging small target. Since the discriminative illumination, occluded or imperfect of the feature extraction algorithm, multi-class features of the object are incomplete which increase the false alarm rate of object recognition. How to use the incomplete features such as region and edge for object recognition, the vote of each fragment region contributes to the recognition result according to its reliability. We cast it as a graph search problem and propose a novel evidence accumulation algorithm to efficiently solve it.