Share Email Print

Proceedings Paper

Keypoint clustering for robust image matching
Author(s): Sundeep Vaddadi; Onur Hamsici; Yuriy Reznik; John Hong; Chong Lee
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A number of popular image matching algorithms such as Scale Invariant Feature Transform (SIFT)1 are based on local image features. They first detect interest points (or keypoints) across an image and then compute descriptors based on patches around them. In this paper, we observe that in textured or feature-rich images, keypoints typically appear in clusters following patterns in the underlying structure. We show that such clustering phenomenon can be used to: 1) enhance recall and precision performance of the descriptor matching process, and 2) improve convergence rate of the RANSAC algorithm used in the geometric verification stage.

Paper Details

Date Published: 7 September 2010
PDF: 12 pages
Proc. SPIE 7798, Applications of Digital Image Processing XXXIII, 77980K (7 September 2010); doi: 10.1117/12.862359
Show Author Affiliations
Sundeep Vaddadi, Qualcomm Inc. (United States)
Onur Hamsici, Qualcomm Inc. (United States)
Yuriy Reznik, Qualcomm Inc. (United States)
John Hong, Qualcomm Inc. (United States)
Chong Lee, Qualcomm Inc. (United States)

Published in SPIE Proceedings Vol. 7798:
Applications of Digital Image Processing XXXIII
Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top