Solving the over segmentation problem in applications of Watershed Transform

Mariela Azul Gonzalez, Gustavo Javier Meschino, Virginia Laura Ballarin

Abstract


Background: The Watershed Transform consists of an image partitioning into its constitutive regions. This transform is easily adapted to be used in different types of images and it allows distinguishing complex objects. However, the implementation of the Watershed Transform for very complex images actually produces over-segmentation. In this paper we propose two algorithms to solve this over-segmentation problem.

Methods: We define internal markers, by algorithms based on clustering and fuzzy logic in order to join the over-
segmented regions with statistical features. To define the algorithm parameters and evaluate their performance, errors against images segmented manually were measured and ROC curves were determined.

Results: The results show that the proposed methods self-adapt to the different image objects characteristics. An improvement of the accuracy is obtained.

Conclusions: This analysis will contribute in images segmentation where complexity of the objects is high.

Full Text: PDF DOI: 10.5430/jbgc.v3n3p29

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

Journal of Biomedical Graphics and Computing
ISSN 1925-4008 (Print)   ISSN 1925-4016 (Online)
Copyright © Sciedu Press 
To make sure that you can receive messages from us, please add the 'Sciedu.ca' domain to your e-mail 'safe list'. If you do not receive e-mail in your 'inbox', check your 'bulk mail' or 'junk mail' folders