Walsh orthogonal moments for efficiently reducing Gibbs noise in image reconstruction

Bing He; Jiangtao Cui; Yanguo Peng

doi:10.1117/12.2541536

27 November 2019 Walsh orthogonal moments for efficiently reducing Gibbs noise in image reconstruction

Bing He, Jiangtao Cui, Yanguo Peng

Proceedings Volume 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence; 113210J (2019) https://doi.org/10.1117/12.2541536
Event: The Second International Conference on Image, Video Processing and Artifical Intelligence, 2019, Shanghai, China

Abstract

Orthogonal moments have been extensively used as global feature-extraction descriptors in two-dimensional image reconstruction. However, a common problem for the existing image moments including orthogonal moments built in Cartesian coordinate system and radial orthogonal moments achieved at polar coordinate space is that Gibbs effect will occur, when image reconstruction is performed using features extracted from finite-order moments. It is well known that Gibbs noise can affect the capability of representation for image moments and the quality of reconstructed images. In this paper, we propose a set of novel orthogonal moments named as Walsh orthogonal moments (WOMs). The basis functions of Walsh orthogonal moments are Walsh functions, which composed of a class of complete orthogonal discontinuous binary function systems. Therefore, it provides possibility of avoiding calculating high order polynomials, and experimental results show Gibbs noise can be efficiently avoided by using discontinuous functions as the basis functions of Walsh orthogonal moments.

Citation Download Citation

Bing He, Jiangtao Cui, and Yanguo Peng "Walsh orthogonal moments for efficiently reducing Gibbs noise in image reconstruction", Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113210J (27 November 2019); https://doi.org/10.1117/12.2541536

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available