Tampere University of Technology

TUTCRIS Research Portal

Texture detection in noisy images by combining several local parameters

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publication2015 2nd International Scientific-Practical Conference Problems of Infocommunications Science and Technology, PIC S and T 2015 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages230-233
Number of pages4
ISBN (Electronic)9789669751928
DOIs
Publication statusPublished - 14 Dec 2015
Publication typeA4 Article in a conference publication
Event2nd International Scientific-Practical Conference Problems of Infocommunications Science and Technology, PIC S and T 2015 - Kharkiv, Ukraine
Duration: 13 Oct 201515 Oct 2015

Conference

Conference2nd International Scientific-Practical Conference Problems of Infocommunications Science and Technology, PIC S and T 2015
CountryUkraine
CityKharkiv
Period13/10/1515/10/15

Abstract

A problem of detecting textural areas in images corrupted by noise is considered. Detection is based on joint use of several local parameters calculated in scanning windows (blocks) of different size. Trained support vector machine (SVM) classifier is used for combining local parameters. Factors that influence detector performance are analyzed. It is shown that detector performance can be improved by taking into account information from classifier output for neighbor pixels.

Keywords

  • image, local parameters, noise, SVM, texture detection