Learning Object Shape: From Drawings to Images
Authors:
- 10 July 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 2064-2071
Abstract
We consider the important challenge of recognizing a variety of deformable object classes in images. Of fundamental importance and particular difficulty in this setting is the problem of "outlining" an object, rather than simply deciding on its presence or absence. A major obstacle in learning a model that will allow us to address this task is the need for hand-segmented training images. In this paper we present a novel landmark-based, piecewise-linear model of the shape of an object class. We then formulate a learning approach that allows us to learn this model with minimal user supervision. We circumvent the need for hand-segmentation by transferring the shape "essence" of an object from drawings to complex images. We show that our method is able to automatically and effectively learn and localize a variety of object classes.Keywords
This publication has 15 references indexed in Scilit:
- Object Recognition with Features Inspired by Visual Cortex2005
- Shape Matching and Object Recognition Using Low Distortion Correspondences2005
- OBJ CUT2005
- SCAPE2005
- The pyramid match kernel: discriminative classification with sets of image features2005
- Object class recognition by unsupervised scale-invariant learning2003
- A metric for distributions with applications to image databases2002
- Efficient matching of pictorial structures2002
- Finding Deformable Shapes Using Loopy Belief Propagation2002
- Modeling by shortest data descriptionAutomatica, 1978