基于小波变换的多尺度水平集算法研究

Multiresolution Level Set Studying Based on Wavelet Transform

针对传统水平集算法在处理低对比度图像时,出现的在局部梯度极大值区域及虚假边缘处停止演化等问题,提出了一种基于小波变换的多尺度水平集算法.采用高斯函数的导函数作为小波函数,使用独立强度传播模型来估计小波函数每一点尺度因子的值,再将沿x,y两个方向小波变换模的递减函数作为水平集速度停止项,对待处理图像进行水平集演化运算.实验结果表明,该方法优于传统水平集变换法.

A new level set way based on multiresolution wavelet transform was proposed, in order to solve the problem of the level set that will often converge to the local gradient maximum region or fake edges.First, the gauss derived function was used as wavelet function to get some different scale and directional images. Second, the intensity dependent spread（IDS） model was used to estimate the value of scale factors. Then, using the decreasing function of x, y two direction wavelet transforms modulus as the stop item and evolves the level set function. Finally, the experimental results showed that the developed algorithm is verified better than the traditional one.