Iterative thresholding based image segmentation using 2D improved Otsu algorithm

Threshold based segmentation methods can effectively separate objects from the background. The conventional Otsu´s method can achieve good result only when the histogram of an image has two distinct peaks. In this paper, an iterative thresholding based on 2D improved Otsu method using a novel threshold value recognition function is proposed which is used to find the optimum threshold value in different types of histograms and separate into two classes. For the two classes separated by the above threshold value, mean values are computed. Based on the threshold value and the two mean values, the histogram of an image is divided iteratively into three regions, namely, the Foreground (FG) region, Background (BG) region and To-Be-Processed (TBP) region. The pixels greater than the larger mean belongs to FG region, the pixel which are lesser than the smaller mean belongs to BG region. The pixel that lies between the two mean values belongs to the TBP region and only this region is processed at next iteration, the FG and BG region are not processed further. Again for that TBP region, the novel threshold value recognition function is used to find a new threshold value and then the two mean values are computed to separate into three classes, namely, the FG, BG and TBP region. Then the new TBP region is processed in a similar manner iteratively until the two mean values computed at successive iterations are not changed. Finally all the previously determined foreground regions are combined separately and the background regions are combined separately to give the segmented image. The experimental results show that the proposed method performs well in detecting the objects and has better anti-noise performance compared with the existing methods.