基于Chan-Vese模型的目标多层次分割算法

An Algorithm for Multi-layer Object Segmentation Based on Chan-Vese Model

由于单一水平集只能通过其符号表达目标和背景两个区域,因此采用单水平集的Chan和Vese(C-V)模型无法分割出目标内部的子目标。为此,提出了基于C-V模型的目标多层次算法。首先给出了目标多层次分割策略;然后,提出了实现本策略的关键技术———背景填充技术,并从其视觉原理、技术实现和理论证明3个方面详细进行了论述;最后,将该技术与C-V模型相结合,提出了目标多层次分割算法;实验结果表明,本文算法能够实现目标多层次分割,并对目标内部含有弱目标的图像特别有效。

The model proposed by Chan and Vese using one level set function is not able to obtain sub-objects in the object because one level set can only represent one object and one background via its sign. To solve the problem, an algorithm for multi-layer object segmentation based on Chan-Vese （C-V） model is proposed. Firstly, an idea for multi-layer object segmentation is proposed after the analysis of the C-V model. Secondly, a key technique, named as the technique of painting background, is developed and proved following the theory of the simultaneous brightness contrast. Thirdly, the proposed algorithm is presented using the proposed technique and the C-V model. Finally, experimental results show that the proposed algorithm is especially effective for the detection of the sub-objects with weak boundaries in the object.