Many-to-one contour matching for describing and discriminating object shape
Authors:
- 1 June 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1673-1680
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.Keywords
This publication has 9 references indexed in Scilit:
- A shape-based object class model for knowledge transfer2009
- Multiscale Categorical Object Recognition Using Contour FragmentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- A discriminatively trained, multiscale, deformable part model2008
- Decomposition, discovery and detection of visual categories using topic models2008
- Untangling Cycles for Contour Grouping2007
- Learning Object Shape: From Drawings to Images2006
- An Implicit Shape Model for Combined Object Categorization and Segmentation2006
- Histograms of Oriented Gradients for Human Detection2005
- LOCUS: learning object classes with unsupervised segmentation2005