Abstract

In this paper, we propose a very efficient method to learn shape mod- els using local curve segments with multiple types of distance metrics. Our learn- ing approach includes two key steps: feature generation and model pursuit. In the first step, for each category, we first extract a massive number of local “prototype” curve segments from a few roughly aligned shape instances. Then we quantize these curve segments with three types of distance metrics corresponding to dif- ferent shape deformations. In each metric space, the quantized curve segments are further grown (spanned) into a large number of ball-like manifolds, and each of them represents a equivalence class of shape variance. In the second step of shape model pursuit, using these manifolds as features, we propose a fast greedy learning algorithm based on the information projection principle. The algorithm is guided by a generative model, and stepwise selects the features that have max- imum information gain. The advantage of the proposed method is identi fied on several public datasets and summarized as follows. (1) Our models consisting of local curve segments with multiple distance metrics are robust to the various shape deformations, and thus enable us to perform robust shape classi fication and detect shapes against background clutter. (2) The auto-generated curve-based fea- tures are very general and convenient, rather than designing speci fic features for each category.