Weight Clustering Histogram Equalization for Medical Image Enhancement

Abstract

Contrast enhancement is important and useful for medical images. One of the widely accepted contrast enhancement method is histogram equalization (GHE). Although GHE achieves comparatively better performance on almost all types of image, GHE sometimes produces excessive visual deterioration. Some extensions of GHE are developed, however these extensions sometimes either fail to enhance the visualization or over enhance contrast of the original image. By over-enhancing contrast, some important information may be lost. Therefore we propose a new method called "Weight Clustering Histogram Equalization" (WCHE). WCHE assigns each non-zero bin of the original image's histogram to a separate cluster, and computes each cluster's weight. The cluster numbers are reduced by three suggesting criteria. Then, the clusters acquire the same partitions as the result image histogram. Finally, transformation functions for each cluster's sub-histogram are calculated based on the traditional GHE method in the new acquired partitions of the result image histogram, and the sub-histogram's gray levels are mapped to the result image by the corresponding transformation functions. We showed experimentally that WCHE bas been validated with some numerical results.