针对Gradient vector field Snakes模型轮廓线需人工初始化的问题及GVF场强分布不合理所导致的模型效率低下和角点定位精度低的问题,在分析GVF场强分布和模型迭代变形原理的基础上,改进原始GVF Snakes模型:模型以SUSAN算法提取的边缘点集构建GVF Snakes模型的初始化轮廓线;并依据图像SUSAN边缘线和模型迭代变形原理局部修正和整体调整GVF场强分布,以符合模型高效迭代变形和对角点、细边缘精确定位的需要。理论分析和实验结果表明,改进GVF的自动Snakes模型提高了模型的计算效率,对细边缘和角点有更高的定位精度。

To address issues about the initialization of Snakes' contour,computational inefficiency,and poor positioning accuracy of the traditional gradient vector field Snakes model,an improved GVF Snakes Model is proposed based on the analysis of the distribution and the deformation principle of the model.In the new model,edges are detected exploiting the SUSAN algorithm firstly:afterwards,a snake contour is initialized using the convex hull generated by the edge points.Then,according to the edges and the deformation principle,the model modifies the distribution of the GVF.Finally,the improved model detects the edges of synthetic images and natural images accurately.The experimental results show that the proposed model not only is efficient,but also has better performance on the weak edges and sharp corners.