원문정보
초록
영어
This paper presents a novel image segmentation method that performs histogram thresholding based on the conception of Tsallis generalized divergence. Firstly, to fit the image segmentation task, the original formula of Tsallis divergence was simplified, and then the symmetrical version was constructed. After that, the criterion of divergence sum of the objective and background between original and thresholded image was set up based on the symmetrical version of the Tsallis divergence. The optimal threshold obtained by minimizing the criterion of divergence sum. Finally, the proposed method was tested on different gray level images, and the performance was evaluated using uniformity measure, shape measure, and CPU run time. Experimental results indicate the effectiveness of the proposed method.
목차
1. Introduction
2. Thresholding Principle based on Tsallis Divergence
2.1. Tsallis Divergence
2.2. Image Thresholding
3. Experimental Results and Performance Evaluation
3.1. Experimental Results and Analysis
3.2. Performance Evaluation
5. Conclusion
Acknowledgements
References