一种新结构下的主动轮廓算法

经典主动轮廓模型是采用由内部能量和外部能量共同组成的能量函数来进行收敛计算的，其中外部能量对精确收敛到目标轮廓起决定性作用，而内部能量在保证轮廓线进行合理变动的同时，却对收敛精确性产生了负作用。为克服这一问题，因而给出一种新的主动轮廓结构，即先把内部能量从能量函数中分离出来，仅采用外部能量进行收敛计算，然后在此结构下重新定义图像能量和控制能量，同时引入了轮廓修正函数，把连续性和光滑性约束应用到Snake曲线的变动过程之中。仿真实验表明，新结构下的主动轮廓算法对初始轮廓要求不高，具有收敛速度快、跟踪精度高等优点。

An Active Contour Algorithm under New Structure

The energy function of the classical active contour model is composed of the internal energy and the external energy, the internal energy is used to restrict the Snake shaping and the external energy leads the convergence process of active contour. Actually, the convergence accuracy of the objective contour is mainly determined by the external energy, while the internal energy is only to ensure that the contour shapes with reason. Because the internal energy includes a few unrelated factors, it has some side-effect on the convergence accuracy of the objective contour. So in this paper a new active contour structure is presented to solve the problem, in which the internal energy is separated from energy function, only the external energy is applied to the convergence process of active contour, at the same time the image energy and the control energy are redefined, a revised contour function is introduced, the continuity and smoothness is embodied in the Snake shaping process. Experimental results show that the active contour algorithm under new structure is little dependent on the initial contour and can converge quickly; the number of control points adaptively changes also can increase the tracking accuracy of objective contour.