Share Email Print
cover

Proceedings Paper

Non-iterative normalized feature extraction in large viewpoint variances based on PCA of gradient
Author(s): Jian Zhang; Song Cao; Di Wen
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Effective local feature extraction is one of the fundamental tools for retrieval applications in computer vision. However, it is difficult to achieve distinguishable local features in large viewpoint variances. In this paper, we propose a novel non-iterative approach of normalized feature extraction in large viewpoint variances, which adapts local regions to rotation, scale variance and rigid distortion from affine transformation. Our approach is based on two key ideas: 1) Localization and scale selection can be directly achieved with the centroid and covariance matrix of the spatial distribution of pixels in a local region. 2) Principal Component Analysis (PCA) on gradients of intensity gives information on texture, thus it can be used to get a resampled region which is isotropic in terms of variance of gradient. Experiments demonstrate that our normalized approach has significant improvement on matching score in large viewpoint variances.

Paper Details

Date Published: 21 March 2013
PDF: 8 pages
Proc. SPIE 8664, Imaging and Printing in a Web 2.0 World IV, 86640I (21 March 2013); doi: 10.1117/12.2009927
Show Author Affiliations
Jian Zhang, Tsinghua Univ. (China)
Song Cao, Univ. of California, Los Angeles (China)
Di Wen, Tsinghua Univ. (China)


Published in SPIE Proceedings Vol. 8664:
Imaging and Printing in a Web 2.0 World IV
Qian Lin; Jan P. Allebach; Zhigang Fan, Editor(s)

© SPIE. Terms of Use
Back to Top