Image Segmentation Based On Gray-Level Spatial Correlation Maximum Between-Cluster Variance

When processing the background and target blurred image, 1D-Otsu and 2D-Otsu segmentation effect is not good. The proposed algorithm used the gray value of the pixels and their similarity with neighboring pixels in gray value to build a histogram which was called gray-level spatial correlation histogram. Then threshold value is obtained by calculating GLSC histogram maximum between-class variance. Integral figure was introduced in order to make the time complexity from original O((N(2)xL)(2)) to O(N(2)xL). The experimental results show that the proposed method image segmenting is better than 1D-Otsu and 2D-Otsu, when processing the background and target blurred image.