Learning feature distance measures for image correspondences

• Published in: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) Vol. 2; pp. 560 - 567 vol. 2
• Main Authors: Chen, X., Cham, T.-J.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 2005
• Subjects: Content based retrieval; Histograms; Image matching; Image retrieval; Measurement standards; Object detection; Optimization methods; Pixel; Testing; Training data
• ISBN: 0769523722; 9780769523729
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2005.205

Standard but ad hoc measures such as sum-of-squared pixel differences (SSD) are often used when comparing and registering two images that have not been previously observed before. In this paper, we propose a framework to address the problem of learning a parametric feature distance measure to measur...