Share Email Print
cover

Proceedings Paper

Image denoising using local tangent space alignment
Author(s): JianZhou Feng; Li Song; Xiaoming Huo; XiaoKang Yang; Wenjun Zhang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We propose a novel image denoising approach, which is based on exploring an underlying (nonlinear) lowdimensional manifold. Using local tangent space alignment (LTSA), we 'learn' such a manifold, which approximates the image content effectively. The denoising is performed by minimizing a newly defined objective function, which is a sum of two terms: (a) the difference between the noisy image and the denoised image, (b) the distance from the image patch to the manifold. We extend the LTSA method from manifold learning to denoising. We introduce the local dimension concept that leads to adaptivity to different kind of image patches, e.g. flat patches having lower dimension. We also plug in a basic denoising stage to estimate the local coordinate more accurately. It is found that the proposed method is competitive: its performance surpasses the K-SVD denoising method.

Paper Details

Date Published: 5 August 2010
PDF: 10 pages
Proc. SPIE 7744, Visual Communications and Image Processing 2010, 774423 (5 August 2010); doi: 10.1117/12.863472
Show Author Affiliations
JianZhou Feng, Shanghai Jiao Tong Univ. (China)
Li Song, Shanghai Jiao Tong Univ. (China)
Xiaoming Huo, Georgia Institute of Technology (United States)
XiaoKang Yang, Shanghai Jiao Tong Univ. (China)
Wenjun Zhang, Shanghai Jiao Tong Univ. (China)


Published in SPIE Proceedings Vol. 7744:
Visual Communications and Image Processing 2010
Pascal Frossard; Houqiang Li; Feng Wu; Bernd Girod; Shipeng Li; Guo Wei, Editor(s)

© SPIE. Terms of Use
Back to Top