利用椭圆性质提取椭圆

The Dynamic Searching Optimization Image Reconstruction Method on the Condition of Maximum Entropy

基于在文献［１］中开发的曲线提取算法的框架，并利用由椭圆的极点—极线性质开发的三点组到椭圆参数的收敛映射，我们开发了一个鲁棒地从直接提取椭圆的以随机Ｈｏｕｇｈ变换（ＲＨＴ）和椭圆性质为基础的椭圆提取新技术。用精确仿真的计算机图象和真实图象进行的大量实验证明了该技术的正确性。

This paper presents a kind of dynamic searching image reconstruction method that satisfies several criteria. From the image space essence, this paper establishes three criterion functions. The entropy function derivative isn't a linear function, this paper presents a method that transforms it to a proximate linear formula and gets a iteration formula.The dynamic searching method, to the best, avoids the adjustment overdose or insufficiency problem in the course of iteration that exists in many iteration methods.