Bilateral tangent projection for manifold smoothing

Yi Hu, Lei Lei, Won Jae Park, Sung Jea Ko

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a bilateral tangent projection (BTP) algorithm to smooth a set of noisy data assumed to lie on a low-dimensional manifold. The data points are smoothed by a family of local tangent projections adaptively. The BTP algorithm utilizes not only the location information of the data point but also the fitness of the tangent space estimation. The local tangent space with better fitness plays more important role in the smoothing procedure. The experimental results show that our algorithm is effective for noise reduction and preserves the structure of the underlying manifold.

Original languageEnglish
Title of host publicationProceedings - 4th International Congress on Image and Signal Processing, CISP 2011
Pages2210-2213
Number of pages4
DOIs
Publication statusPublished - 2011
Event4th International Congress on Image and Signal Processing, CISP 2011 - Shanghai, China
Duration: 2011 Oct 152011 Oct 17

Publication series

NameProceedings - 4th International Congress on Image and Signal Processing, CISP 2011
Volume4

Other

Other4th International Congress on Image and Signal Processing, CISP 2011
CountryChina
CityShanghai
Period11/10/1511/10/17

Keywords

  • denoising
  • manifold learning
  • manifold smoothing

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint Dive into the research topics of 'Bilateral tangent projection for manifold smoothing'. Together they form a unique fingerprint.

  • Cite this

    Hu, Y., Lei, L., Park, W. J., & Ko, S. J. (2011). Bilateral tangent projection for manifold smoothing. In Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011 (pp. 2210-2213). [6100601] (Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011; Vol. 4). https://doi.org/10.1109/CISP.2011.6100601