Median-based image thresholding
Jinghao Xue and Mike Titterington
Image and Vision Computing
In order to select an optimal threshold for image thresholding that is relatively robust to the presence of skew or heavy-tailed class-conditional distributions, we propose two median-based approaches: one is an extension of Otsu's method, and the other is an extension of Kittler and Illingworth's minimum error thresholding. The two extensions preserve the methodological simplicity and computational efficiency of their original methods. Experiments on some real images and simulated data-sets show that the two extensions can achieve robust performance. In addition, we provide theoretical interpretation of the new approaches, based on the mixture of Laplace distributions.