Publications

Outline-Based Part Segmentation Using Intermediate-Level Symmetries

Guillaume-Alexandre Bilodeau and Robert Bergevin

Abstract - A new part segmentation approach is presented which works on real 2D images. These images may contain a complex foreground 3D object with textures and shadows on a cluttered background. The proposed approach relies on the outline of the object to guide the grouping of lines using symmetry and colinearity principles. This grouping of lines leads to simple shapes which could be modeled by 3D primitives such as geons or general cylinders. An algorithm implemented on the basis of this approach appears robustto noise and generic conditions. Besides, intermediate-level symmetries employed by the algorithm ensure a good robustness to internal textures and markings. The results obtained demonstrate the validity of the approach as a mean towards 3D generic objectrecognition from real 2D images.

Bibtex:

@inproceedings{Bilodeau75,
author    = { Guillaume-Alexandre Bilodeau and Robert Bergevin },
title     = { Outline-Based Part Segmentation Using Intermediate-Level Symmetries },
booktitle = { 12th Conference on Vision Interface },
volume    = { 1 },
pages     = { 66-73 },
year      = { 1999 },
month     = { May 18-21 },
location  = { Trois-Rivières, Canada }
}

Last modification: 2002/07/08 by bilodeau

		Home \| About \| People \| Research \| Publications \| Events \| Profile
		©2002-. Computer Vision and Systems Laboratory. All rights reserved