Entropy: a new definition and its applications

Shannon’s definition of entropy is critically examined and a new definition of classical entropy based on the exponential behavior of information-gain is proposed along with its justification. The concept is then extended to gray tone image for defining its global, local and conditional entropy. Based on these definitions four algorithms for object extraction are developed and implemented. One of these algorithms uses a Poisson distribution-based model of an ideal image. Finally, a concept of positional entropy giving an information regarding the location of an object in a scene is introduced.