Please use this identifier to cite or link to this item:
Title: WaterBalloons: a hybrid watershed balloon snake segmentation
Authors: Dagher, Issam 
Tom, Kamal El
Affiliations: Department of Computer Engineering 
Keywords: Merging
Surface topography
Active contours
Surface morphology
Object detection
Optimization methods
Underwater tracking
Subjects: Image segmentation
Neural networks (Computer science)
Issue Date: 2008
Part of: Image and vision computing
Volume: 26
Issue: 7
Start page: 905
End page: 912
In this paper, a new image segmentation technique called WaterBalloons is introduced. It combines both Watershed segmentation and the Active Contour Model known as Balloon Snake. The Watershed transform has a major problem of over-segmentation. Solutions like Region merging, use of markers, use of multi-scales have been proposed. These approaches led to other problems such as under-segmentation. The Balloon Snake in an innovative approach that detects salient objects in an image. But in general Snakes are very sensitive to initialization and need user interactions and a-priori knowledge of objects to segment. WaterBalloons provide the advantage of reducing watershed over-segmentation problems while preventing under-segmentation and ensure automatic initialization of traditional snakes. In addition, a method for parameter optimization of the proposed hybrid snake is introduced based on energy transitions tracking.
This paper was presented in " Proceedings of International Conference on Neural networks. August 12-17, 2007. Orlando, USA ".
Ezproxy URL: Link to full text
Type: Journal Article
Appears in Collections:Department of Computer Engineering

Show full item record

Record view(s)

checked on Jun 6, 2023

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.