Hands-On Image Processing with Python

Computing the local entropy

Entropy is a measure of uncertainty or randomness in an image. It is mathematically defined as follows:

In the previous formula, p_i is the probability (obtained from the normalized histogram of the image) associated with the gray-level, i. This formula computes the global entropy of an image. In a similar manner, we can define local entropy too, to define local image complexity, and it can be computed from the local histograms.

The skimage.rank.entropy() function computes the local entropy (the minimum number of bits required to encode local gray-level distribution) of an image on a given structuring element. ...