Wavelet Noise Reduction Based on Energy Features

Fu, G. and Hojjatoleslami, A. and Colchester, A.C.F. (2008) Wavelet Noise Reduction Based on Energy Features. In: 5th International Conference, ICIAR 2008, 25-27th June 2008, Povoa de Varzim, Portugal. (The full text of this publication is not available from this repository)

The full text of this publication is not available from this repository. (Contact us about this Publication)

Abstract

This paper proposes a new method to detect or segment local bright and dark objects using the detail map reconstructed from the wavelet detail sub-bands after wavelet coefficient shrinkage. We found that the reconstructed detail map has the reliable zero-crossing properties at multi-scale edges. We propose the shrinkage of wavelet coefficients based on energy features to remove noise while preserving the details. The local bright and dark objects can be detected by a simple threshold applied on the detail map. The results show that the performance of our method is very promising despite simple structure.

Item Type: Conference or workshop item (Paper)
Uncontrolled keywords: noise reduction; energy feature; device noise profile
Subjects: T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image Analysis, Image Processing
Divisions: Faculties > Science Technology and Medical Studies > Kent Institute of Medicine and Health Sciences (KIMHS)
Depositing User: M.P. Stone
Date Deposited: 24 Mar 2009 15:23
Last Modified: 16 Jun 2011 12:33
Resource URI: http://kar.kent.ac.uk/id/eprint/11932 (The current URI for this page, for reference purposes)
  • Depositors only (login required):