Enhanced Lane: Interactive Image Segmentation by Incremental Path Map Construction

 

Hyung W. Kang and Sung Yong Shin

 

 

 Abstract

 

Live-wire type techniques for interactive image segmentation are of practical use for various applications such as medical image analysis, digital image composition, etc. Intelligent scissors and live wire are the representative techniques of this type, which are based on a graph search over an entire image. Another technique called live lane is also based on a graph search but localizes the search domain to give an interactive feedback. Compared to the live wire, the live lane trades off the repeatability of segmentation for its time efficiency. In this paper, we present a novel image segmentation technique called enhanced lane, a modified version of the live lane that ensures both efficiency and repeatability. By restricting the search domain and updating the path map incrementally, the enhanced lane can extract objects from an image interactively with its efficiency comparable to that of the live lane while also keeping its repeatability comparable to that of the live wire. Based on the live lane paradigm, our technique also differs from the time-efficient version of live wire called live wire on the fly: the enhanced lane always guarantees strictly bounded response time regardless of the image size and follows the target boundary with little digression which leads to better repeatability.

 

 Keywords

 

Interactive image segmentation, Livewire, Intelligent Scissors, Dynamic programming, Graph search

 

 Paper

 

Paper in PDF

 

 Citation

 

H. Kang and S. Y. Shin. "Enhanced Lane: Interactive Image Segmentation by Incremental Path Map Construction". Graphical Models, Vol. 64, No. 5, pp. 282-303, 2002.

 

@article{Kang:2002:EL,
author = {Hyung W. Kang and Sung Yong Shin},
title = {Enhanced Lane: Interactive Image Segmentation by Incremental Path Map Construction},
journal = {Graphical Models},
volume = {64},
number = {5},
pages = {282-303},
year = "2002"

}