An Improved Image Segmentation Algorithm Based on Local Gaussian Distribution Fitting Energy Model

Abstract

The active contours driven by local Gaussian distribution fitting (LGDF) energy segmentation method can effectively handle brain tumors and other medical image segmentation. But this method needs a manual initial contour and is more sensitive to the position of the initial contour. It may fail to segment the target image when the initial contours are inappropriate. Therefore, an improved method based on LGDF model is proposed. It combines the unsupervised learning algorithm of K-means clustering algorithm with the LGDF segmentation algorithm. First the K-means clustering algorithm is used to get the primary segmentation and make it as the initial contour position of LGDF model instead of a manual one. Then the LGDF model is used for fine segmentation based on the coarse segmentation of clustering algorithm so as to get an accurate segmentation result. The experimental results show that the proposed method could obtain segmentation automatically rather than manually labeling of the initial contour, and satisfied results are obtained with less calculation time.