用于图像分割的自适应距离保持水平集演化

Li等人提出的距离保持水平集方法有传统变分水平集方法不具备的许多优点,然而,它有初始曲线必须包围目标物体或完全置于目标物体内部或外部的缺点.提出一种自适应距离保持水平集方法,它无须初始曲线包围目标物体或完全置于目标物体内部或外部,即初始曲线可以置于图像的任何地方.它能够解决原方法所不能解决的一些图像分割问题,例如,能够从任意选取的一条初始曲线出发自动检测目标物体的内外轮廓,检测多目标物体以及深度凹陷区域的边缘,并能较好地提取目标物体的弱边界.对几幅具有不同目标边界形态的合成图像和自然图像进行了实验,结果都取得了预期的分割效果.

Adaptive Distance Preserving Level Set Evolution for Image Segmentation

The distance preserving level set method proposed by Li et al. has many advantages over the traditional variational level set methods. However, it has the disadvantage of requiring the initial curve to surround (let in or keep out) the objects to be detected. In this paper, an adaptive distance preserving level set method is proposed, in which the initial curve is no longer required to surround (let in or keep out) the objects to be detected, i.e., the initial curve can be anywhere in the image. The proposed method can detect certain object boundaries, for which the original method is not applicable. E.g. it can automatically detect interior and exterior contours of an object and edges of multi-objects, starting with only one initial curve whose position is anywhere in the image. Moreover, active contours can move into boundary concavities and perform better in the presence of weak boundaries. The proposed method has been applied to synthetic and real images of different object boundaries with promising results.