An infrared image segmentation algorithm based on spatial correlative information

Keyong Wang*, Chengtian Song, Jiahao Deng

*Corresponding author for this work

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

Abstract

Image segmentation is an important technique for image processing and computer vision. The principles of 1-D Otsu's algorithm and thresholding through index of fuzziness are described. Since the infrared images of tank have low object-background contrasts and blurred boundaries in the complex background condition, an adaptive algorithm for image thresholding through index of fuzziness, which is combined with the spatial correlative information, is proposed. The new method makes full use of the spatial correlation of pixels, so that it can extract the detail of the image from the complex background effectively, and improve the accuracy of the segmentation. The results of experiments prove that the presented algorithm has better performance and better robustness against noise.

Original languageEnglish
Title of host publicationFrontiers of Manufacturing and Design Science
Pages3274-3278
Number of pages5
DOIs
Publication statusPublished - 2011
Event2010 International Conference on Frontiers of Manufacturing and Design Science, ICFMD2010 - Chongqing, China
Duration: 11 Dec 201012 Dec 2010

Publication series

NameApplied Mechanics and Materials
Volume44-47
ISSN (Print)1660-9336
ISSN (Electronic)1662-7482

Conference

Conference2010 International Conference on Frontiers of Manufacturing and Design Science, ICFMD2010
Country/TerritoryChina
CityChongqing
Period11/12/1012/12/10

Keywords

  • Fuzzy threshold
  • Image segmentation
  • Spatial correlative information

Fingerprint

Dive into the research topics of 'An infrared image segmentation algorithm based on spatial correlative information'. Together they form a unique fingerprint.

Cite this