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 language | English (US) |
---|---|
Title of host publication | Proceedings of the 2007 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2007 |
Pages | 383-389 |
Number of pages | 7 |
State | Published - 2007 |
Event | 2007 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2007 - Las Vegas, NV, United States Duration: Jun 25 2007 → Jun 28 2007 |
Other
Other | 2007 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2007 |
---|---|
Country | United States |
City | Las Vegas, NV |
Period | 6/25/07 → 6/28/07 |
All Science Journal Classification (ASJC) codes
- Computer Graphics and Computer-Aided Design
- Computer Vision and Pattern Recognition