Mean-variance blind noise estimation for CT images

Alex Pappachen James, A. P. Kavitha

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

Abstract

Noise estimation is a precursor to de-noising techniques to improve the signal and visual quality of medical images. We present a noise estimation algorithm using the local image statistics of the CT images at voxel level. The algorithm calculates the local mean variance distribution and detects the minimised error rates for identifying the tolerance range of voxel to artificial noises. The reliability of the method is experimentally verified using Gaussian noise and Speckle noise on CT scan images.

Original languageEnglish
Title of host publicationAdvances in Signal Processing and Intelligent Recognition Systems
PublisherSpringer Verlag
Pages235-243
Number of pages9
ISBN (Print)9783319049595
DOIs
Publication statusPublished - Jan 1 2014
EventInternational Symposium on Signal Processing and Intelligent Recognition Systems, SIRS 2014 - Trivandrum, India
Duration: Mar 13 2014Mar 15 2014

Publication series

NameAdvances in Intelligent Systems and Computing
Volume264
ISSN (Print)2194-5357

Other

OtherInternational Symposium on Signal Processing and Intelligent Recognition Systems, SIRS 2014
CountryIndia
CityTrivandrum
Period3/13/143/15/14

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Fingerprint Dive into the research topics of 'Mean-variance blind noise estimation for CT images'. Together they form a unique fingerprint.

Cite this