基于共轭梯度的B样条主动轮廓边缘提取

边缘提取是图像识别的基础，为了进一步提高搜索效率和克服主动轮廓模型对初始位置敏感的问题，提出了一种基于共轭梯度的B样条主动轮廓变形边缘提取方法。该方法首先通过人工交互的方式，在目标边缘附近给定一条形状和位置尽量和图像边缘一致的B样条曲线；然后对变形曲线B样条的控制节点进行进化，以取代传统方法中对变形曲线上每一个像素点进行的进化，由于控制节点的数目远远小于曲线上像素点的数目，因而可以大大减少计算次数；最后在梯度矢量场中，对进化曲线附加一共轭梯度力，以加快变形曲线向目标边缘的收敛速度。实验表明，该方法不仅能应对深度凹陷问题，而且边缘提取效率有了较大的提高。

B spline Active Contours Boundary Extraction Based on Conjugate Gradient Vector

Boundary extraction is the foundation of image recognition.A method of B-spline active contours boundary extraction based on conjugate gradient vector is presented.With human-machine interface,it gives a B-spline curve which is close to and similar to the objective edge in shape and location.Rather than evolving deformable curve with every pixel on the curve in conventional method,the proposed method evolves the curve with controlled node points which are much less than pixel points in numbers,so computatio...