Image threshold segmentation method based on gu proved 2-D histogram

Image segmentation plays an essential role in the field of image processing. It is usually a fundamental step for further image processing, image description and recognition for example. According to the analysis of the threshold method for image segmentation based on the traditional 2-D gray-level histogram which partitions the areas with some wrong pixels and processes slowly, the 2-D histogram is improved and a novel threshold method based on this 2-D histogram is brought forward which uses the maximum between-cluster variance as the rule. The experiment shows that the segmentation result of this method is better and its computation time is reduced much.