Efficient graph-based search for object detection

In this paper, we focus on the object localization problem in images given a single hand-drawn example as the object model. We propose a novel framework for shape-based object detection and recognition, which we formulate as a graph-based search problem. In our method, we first propose five preprocessing procedures to reduce the irrelevant edge fragments in cluttered real images that often occur in edge detection. Then we build a graph to represent the edge images. Therefore, our goal is to find the group of adjacent nodes in the graph that match well to the model contours. Finally, we present a new evaluation method to verify the candidate hypotheses. We did experiments on the ETHZ shape classes dataset and the INRIA horses dataset. Experimental results demonstrate that the proposed method achieves not only accurate object detection but also precise contour localization in cluttered real images. Comparisons with other recent template-based matching methods further demonstrate the effectiveness and efficiency of the proposed method.