A symbolic dynamics based approach to pattern recognition in image sequences

Aparna Subbu, Eric E. Keller, Asok Ray

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

Abstract

This paper presents the application of symbolic dynamic analysis to two-dimensional images for the purpose of pattern recognition in temporal image sequences. A specific example of flaw detection in polycrystalline alloys via image sequences obtained from a camera mounted on a microscope is considered. An anomaly measure which indicates the severity of a crack with a quantifiable numerical value was derived using the D-Markov machine. Use of a region-of-interest based analysis of the statistical properties of pixels makes the pre-processing step of image registration redundant. The problem due to the presence of relative motion between successive frames of an image sequence does not significantly affect the detection of a fatigue crack when symbolic dynamics is used. A comparison of the performance of the algorithm in the presence and absence of registration of images is shown.

Original languageEnglish (US)
Title of host publicationProceedings of the 2007 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2007
Pages383-389
Number of pages7
StatePublished - 2007
Event2007 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2007 - Las Vegas, NV, United States
Duration: Jun 25 2007Jun 28 2007

Publication series

NameProceedings of the 2007 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2007

Other

Other2007 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2007
Country/TerritoryUnited States
CityLas Vegas, NV
Period6/25/076/28/07

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'A symbolic dynamics based approach to pattern recognition in image sequences'. Together they form a unique fingerprint.

Cite this