Minimum Square Distance Thresholding Based on Asymmetrical Co-occurrence Matrix
In thresholded image segmentation, correct and adequate extraction of pixel distribution information is the key. In this paper, asymmetrical gray transition co-occurrence matrix is applied to better represent the spatial distribution information of images, and uniformity probability of binarization image is introduced to calculated the deviation information between original and thresholding image. A novel minimum square distance criterion function is proposed to select threshold value, and the vector correlation coefficient is deduced to interpret the reasonable of new criterion. Comparing with relative entropy method, the proposed method is simpler, moreover, it has outstanding object extraction performance.
KeywordsThresholding method Co-occurrence matrix Minimum square distance
This work is supported by the National Science Foundation of China (No. 61571361, 61671377), and the Science Plan Foundation of the Education Bureau of Shaanxi Province (No. 15JK1682).
- 5.El-Feghi, I., Adem, N., Sid-Ahmed, M.A., et al.: Improved co-occurrence matrix as a feature space for relative entropy-based image thresholding. In: Proceedings of the Computer Graphics, Imaging and Visualization, vol. 49, pp. 314–320 (2007). http://doi.org/10.1109/CGIV.2007.49
- 6.Fan, J.L., Ren, J.: Symmetric co-occurrence matrix thresholding method based on square distance. Acta Electronica Sinica 39(10), 2277–2281 (2011). http://en.cnki.com.cn/Article_en/CJFDTOTAL-DZXU201110012.htm. (in Chinese)