基于力场分析的主动轮廓模型

传统Snake模型存在的缺点是，其初始轮廓必须靠近图像中感兴趣目标的真实边缘，否则会得到错误结果，且由于Snake模型的非凸性，结果不能进入感兴趣目标的深凹部分，很容易陷入局部极小点，由此该文提出一种基于力场分析的主动轮廓模型，详细分析了基于欧氏距离变换的距离势能力场分布，归纳出感兴趣目标上真轮廓点与假轮廓点的判别标准，建立了由曲线能量到最终结果的有效方法，避免了Snake陷入局部极小点，实验结果表明，该模型具有较大的捕获区域，能够进入感兴趣目标的深凹部分，准确提取感兴趣目标的轮廓，与GVF Snake模型相比，该模型具有很小的计算量。

Active Contour Models Based on Force Field Analysis

The traditional snake initial contour should be close to the true boundary of interested object in an image, or else it would converge to the wrong result. Next, active contours have difficulties progressing into boundary concavities. Moreover, the traditional snake and its almost kinds of improved methods are easy to get into local minimum because snake models are non-convex. An active contour model based on force field analysis, namely FFASnake model, is presented in this paper. Based on analyzing force distribution rules of distance potential force field, a standard is introduced here to distinguish the false one from contour points. The result is not considered as the final solution when the snake energy is minimal. Furthermore, the estimation and calculation should be done according to the established standard, and then the result can be considered as the final one, so the snake is prevented from running into local minimum. The simulation results show that the FFASnake model has a large capture range, can move a snake into boundary concavities and is able to obtain the interested object contour precisely. Compared with the GVFSnake, this new model has a low calculation cost.