Abstract
In order to improve the proportion of target detection, an adaptive method of automatic threshold selection based on the method of Otsu thresholding is proposed. It takes the gray level statistics of the resultant target and background region as a criterion for discrimination if correct segmentation is obtained. Theoretical analysis shows that correct image segmentation can be obtained for a low-contrast image with complex background using this method, no matter the proportion of the target is high or low. Moreover, the amount of computation and the processing time can be decreased greatly by setting a gray-level selection threshold. Several experimental results are presented to support the validity of this method.
| Original language | English |
|---|---|
| Pages (from-to) | 521-524 |
| Number of pages | 4 |
| Journal | Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology |
| Volume | 23 |
| Issue number | 4 |
| Publication status | Published - Aug 2003 |
Keywords
- Adaptive thresholding
- Image processing
- Image segmentation
- Infrared quiz-image
- Thresholding segmentation