Center for Human Modeling and Simulation

Many-to-one Contour Matching for Describing and Discriminating Object Shape

Jianbo Shi, University of Pennsylvania
Praveen Srinivasan, University of Pennsylvania
QIhui Zhu, University of Pennsylvania

Document Type Conference Paper

Srinivasan, P., Zhu, Q., & Shi, J. IEEE Conference on Computer Vision and Pattern Recognition. 2010.

Abstract

We present an object recognition system that locates an object, identifies its parts, and segments out its contours. A key distinction of our approach is that we use long, salient, bottom-up image contours to learn object shape, and to achieve object detection with the learned shape. Most learning methods rely on one-to-one matching of contours to a model. However, bottom-up image contours often fragment unpredictably. We resolve this difficulty by using many-to-one matching of image contours to a model. To learn a descriptive object shape model, we combine bottom-up contours from a few representative images. The goal is to allow most of the contours in the training images to be many-to-one matched to the model. For detection, our challenges are inferring the object contours and part locations, in addition to object location. Because the locations of object parts and matches of contours are not annotated, they appear as latent variables during training. We use the latent SVM learning formulation to discriminatively tune the many-to-one matching score using the max-margin criterion. We evaluate on the challenging ETHZ shape categories dataset and outperform all existing methods

 

Date Posted: 11 July 2012