摘要： 基于局部特性的分割校正模型能够在图像分割的同时实现对非均匀场的校正,从而对灰度不均匀图像有较好的分割效果,然而,该模型具有局部特性,且采用多相分割,使得活动轮廓曲线对初始位置较为敏感,且分割速度较慢。针对该不足,通过引入自适应距离保持水平集算法,采用分割校正模型与自适应距离保持水平集相结合的方法,提出一种新的快速分割算法。实验结果表明,该算法可摆脱初始轮廓的限制,避免在分割灰度不均匀图像时边缘泄漏和分割不足现象,并且具有分割快速的特点。

关键词: 水平集, 局部特性, 分割校正, 多相分割

Abstract: Segmentation correction model base on local features can implement the correction of intensity inhomogeneity images,for which has better segmentation effect,but with the local features of the proposed model,and using multiphase segmentation,so that it is sensitive to the initial position of the active contour curve and the segmentation is slow.Aiming at the shortage,a new fast segmentation algorithm is proposed by introducing Adaptive Distance Preserving Level Set(ADPLS) algorithm,combining the segmentation correction model and adaptive distance preserving level set method.Experimental results show that the improved algorithm not only gets rid of the influence of the initial contour,but also avoids the edge leakage and segmentation shortage phenomenon,maintains the fast segmentation.

Key words: level set, local characteristic, segmentation correction, multiphase segmentation

中图分类号: 

• TP391.4