Maximum Entropy Threshold

Author: Jerek Sacha (jarek at ieee.org)
History: 2004/02/13: First version
Source: Entropy_Threshold.java
Installation: Download Entropy_Threshold.java to the plugins folder, or subfolder, and compile and run it using Plugins/Compile and Run. Restart ImageJ and there will be a new "Entropy_Threshold" command in the Plugins menu.
Installation: Download Entropy_Threshold.class to the plugins folder, or subfolder, restart ImageJ, and there will be a new Entropy_Threshold command in the Plugins menu.
Description: This plugin does automatic thresholding based on the entopy of the histogram. The method is very similar to Otsu's method. Rather than maximising the inter-class variance, it maximises the inter-class entropy. Entropy is a measure of the uncertainity of an event taking place. You can calculate it as: S = -(sum)p*log2(p) so it is very straightforward to do using the histogram data. (p is the probability of a pixel greyscale value in the image, and (sum) is the greek capital sigma. It is customary to use log in base 2.

See: P.K. Sahoo, S. Soltani, K.C. Wong and, Y.C. Chen "A Survey of Thresholding Techniques", Computer Vision, Graphics, and Image Processing, Vol. 41, pp.233-260, 1988.

|Plugins | Home |