Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Interactive Segmentation TechniquesConclusion and Future Work

Interactive Segmentation Techniques: Conclusion and Future Work [Interactive segmentation techniques have attracted a wide range of interest and applications. Many researchers have worked on this topic to improve the efficiency, robustness, speed, and user-friendliness of interactive segmentation. Image features such as colors, edges, and locations are essential for computers to recognize and extract objects. By employing various principles such as graph-cut, random-walk, or region merging/splitting, interactive segmentation methods attempt to balance two constraints: regional-homogenuity and boundary-inhomogenuity. These two constraints are expressed as a cost function in most segmentation methods which is then optimized locally and/or globally. Satisfactory results can be obtained by incorporating a sufficient amount of user interactions.] http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

Interactive Segmentation TechniquesConclusion and Future Work

Download PDF
2 pages

Loading next page...
 
/lp/springer-journals/interactive-segmentation-techniques-conclusion-and-future-work-2KZTzzCo3t
Publisher
Springer Singapore
Copyright
© The Author(s) 2014
ISBN
978-981-4451-59-8
Pages
75 –76
DOI
10.1007/978-981-4451-60-4_5
Publisher site
See Chapter on Publisher Site

Abstract

[Interactive segmentation techniques have attracted a wide range of interest and applications. Many researchers have worked on this topic to improve the efficiency, robustness, speed, and user-friendliness of interactive segmentation. Image features such as colors, edges, and locations are essential for computers to recognize and extract objects. By employing various principles such as graph-cut, random-walk, or region merging/splitting, interactive segmentation methods attempt to balance two constraints: regional-homogenuity and boundary-inhomogenuity. These two constraints are expressed as a cost function in most segmentation methods which is then optimized locally and/or globally. Satisfactory results can be obtained by incorporating a sufficient amount of user interactions.]

Published: Sep 1, 2013

Keywords: Segmentation accuracy; Robustness of user interaction; Dynamic interaction; 3D image segmentation

There are no references for this article.