Paper
26 February 2008 Multi-model geometrical fitting for wide baseline image matching
Lixin Fan, Timo Pylvänäinen
Author Affiliations +
Proceedings Volume 6813, Image Processing: Machine Vision Applications; 68130H (2008) https://doi.org/10.1117/12.779411
Event: Electronic Imaging, 2008, San Jose, California, United States
Abstract
Local feature-based matching methods have witnessed great success in the context of multiple view matching, object recognition and video content analysis. Naturally, one would like to (1) investigate the merits and shortcomings of feature-based approaches; and (2) to extend such approaches to general object classes matching problems. The present paper illustrates our research attempts along this direction. The proposed feature-based method is empirically justified, and demonstrates excellent robustness against intra-class variation, structure variation, scale change, rotation and background clutter.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lixin Fan and Timo Pylvänäinen "Multi-model geometrical fitting for wide baseline image matching", Proc. SPIE 6813, Image Processing: Machine Vision Applications, 68130H (26 February 2008); https://doi.org/10.1117/12.779411
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Cameras

Motion models

Detection and tracking algorithms

Object recognition

3D image processing

Analytical research

Back to Top