Fuzzy partition of two-dimensional histogram and its application to thresholding.

摘要: Abstract This paper proposes a thresholding approach by performing fuzzy partition on two-dimensional (2D) histogram of the image. The novel 2D method and membership assignment are based relationship two sets characterized set best parameters (a, b, c) , which makes image have maximum entropy. threshold is selected as crossover point region [a, c] . preprocessed moment arrays employed to reduce computation time entropy from O (8 N 2 ) (2 ). proposed has been tested various images, results demonstrated that outperforms nonfuzzy one-dimensional (1D) approach.