基于高斯滤波C-V模型分割算法的改进

在现实世界经常有一些灰度不均匀的图像给图像分割造成了很大的困难.为了解决由于图像灰度不均匀造成的图像轮廓提取的困难,结合邻域算法和高斯滤波的性质的基础上,提出了基于图像局部区域灰度信息的算法,使曲线的演化过程基于图像的局部信息.同时采用了水平集演化规则化模型,避免了水平集函数的不断初始化.实验结果表明,新算法无论对合成图像还是真实图像,都能提取出准确的物体轮廓.

Improvement of C-V segmentation model based on Gaussian filter

In order to overcome the image segmentation difficulties caused by intensity homogeneity in real-world images, a region-based active contour model was proposed which draw upon intensity information in local regions based on neighborhood algorithm and Gaussian filter. This method made the curve evolve based on intensity information in local regions. In addition, the regularity of the level set function avoided expensive reinitialization of the evolving level set function. Experimental results for synthetic and real images show desirable performances of the proposed method.