A Masi-Entropy Image Thresholding Based on Long-Range Correlation

Image thresholding based on entropic concepts is one of the most used segmentation techniques in image processing. The Tsallis and Masi entropies are information measures that can capture long-range interactions in various physical systems, while Shannon entropy is more appropriate for short-range correlations. In this paper, we have improved a thresholding technique based on Tsallis and Shannon formulas by using Masi entropy. Specifically, we replace the Tsallis information measure with Masi's one, obtaining better results than the original methodology. We also compared our results with thresholding methods that use just Masi (or Tsallis) entropy. Quantitative measures of segmentation accuracy demonstrated the superior performance of our method in infrared images and nondestructive testing (NDT) images.