Medical image segmentation based on maximum entropy multi-threshold segmentation optimized by improved cuckoo search algorithm
| Autor: | Tingmei Wang, Yujie Li, Aiju Li, Wenliang Niu |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
business.industry
Segmentation-based object categorization Principle of maximum entropy ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Scale-space segmentation Pattern recognition Image segmentation Computer Science::Computer Vision and Pattern Recognition Entropy (information theory) Segmentation Algorithm design Artificial intelligence Cuckoo search business Algorithm Mathematics |
| Zdroj: | 2015 8th International Congress on Image and Signal Processing (CISP). |
| DOI: | 10.1109/cisp.2015.7407926 |
| Popis: | In order to improve the accuracy of medical image segmentation and overcome the shortcomings of maximum entropy segmentation algorithm, the paper proposes the medical image segmentation based on maximum entropy multi-threshold segmentation optimized by improved cuckoo search algorithm (MCS). Firstly, the maximum entropy method is adopted to find the optimization objective function, then the improved cuckoo search algorithm is used to optimize the objective function, find the best segmentation threshold of the medical image, and achieve medical image segmentation; finally, simulation tests are carried out for a variety of images. The results indicate that the method proposed by the paper can improve the accuracy of medical image segmentation, and have good robustness and good practical value. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|