H.: Linked Edges as Stable Region Boundaries

Many of the recently popular shape based category recognition methods require stable, connected and labeled edges as input. This paper introduces a novel method to find the most stable region boundaries in grayscale images for this purpose. In contrast to common edge detection algo-rithms as Canny, which only analyze local discontinuities in image brightness, our method integrates mid-level infor-mation by analyzing regions that support the local gradient magnitudes. We use a component tree where every node contains a single connected region obtained from thresh-olding the gradient magnitude image. Edges in the tree are defined by an inclusion relationship between nested regions in different levels of the tree. Region boundaries which are similar in shape (i. e. have a low chamfer distance) across several levels of the tree are included in the final result. Since the component tree can be calculated in quasi-linear time and chamfer matching between nodes in the compo-nent tree is reduced to analysis of the distance transforma-tion, results are obtained in an efficient manner. The pro-posed detection algorithm labels all identified edges during calculation, thus avoiding the cumbersome post-processing of connecting and labeling edge responses. We evaluate our method on two reference data sets and demonstrate im-proved performance for shape prototype based localization of objects in images. 1