Dale-Jones R & Tjahjadi T

Image and Vision Computing, vol 10, 1992, 495-507

Abstract

Four algorithms that modify the histogram equalization algorithm, and extend its capability to a larger range of histograms, are presented. The algorithms allow the use to balance the amount of stretching of peaks in the histogram against the amount of information lost. The effect of the algorithms on peaks or Gaussians having various means, standard deviations and population sizes are discussed. The results are compared to applying the local histogram equalization.