关键词: 图像分割, 主动轮廓模型, 区域信息, 拟合中心, 信息熵

Abstract: Image segmentation is one of the key steps in the subsequent image processing. When the background of the target is complex, the traditional active contour model is difficult to segment the image accurately. In order to make the image segmentation more accurately, this paper studies the active contour model, afterwards, proposes an image segmentation method based on improved active contour model with local information. Firstly, the local information is integrated into the energy function of the active contour model to enhance the image segmentation caused by the mutation of the local information. Secondly, the fitting centers of the internal and external curves are improved to reduce the effects of image noise on the accuracy of the fitting center. Finally, to speed up the evolution of the curve, the information entropy is used to enhance the weights inside and outside the curve. Compared with the traditional CV model and other three models, the experimental results show that the proposed model can segment image more accurately, and achieve great advantages in the efficiency of segmentation.

Key words: image segmentation, active contour model, local information, fitting center, information entropy