LCV模型在医学图像分割中的应用

针对C-V模型不能充分利用图像局部区域灰度变化信息从而导致难以准确分割灰度不均物体等缺陷，提出一种基于局部区域的C-V(LCV)模型。利用计算局部窗函数内的加权灰度均值来取代全局均值，并加入约束水平集函数为符号距离函数的能量项，从而避免水平集函数的重新初始化。对医学图像的分割结果证明LCV模型在分割灰度不均物体方面优于C-V模型，其分割效率高于LBF模型。

Application of LCV Model in Medical Image Segmentation

The Chan-Vese(C-V) active contour model utilizes global region information of images, so it is difficult to handle images with intensity inhomogeneity. A Local region-based C-V(LCV) model based on image local region information is proposed, which utilizes the weighted average intensity inside a local window to replace the global average intensity of C-V model. Moreover, the distance penalized energy function is incorporated into it, which makes the expensive re-initialization unnecessary. Experimental results of medical image segmentation show it has a distinctive advantage over C-V model for images with intensity inhomogeneity, and it is more efficient than LBF.