Efficient Optimal Multi-level Thresholding for Biofilm Image Segmentation

Authors:
Darío Rojas;Luis Rueda;Homero Urrutia;Alioune Ngom
Affiliations:
Department of Computer Science, University of Atacama, Copiapó, Chile;School of Computer Science, University of Windsor, Windsor, Canada N9B 3P4;Biotechnology Center and Faculty of Biological Sciences, University of Concepción, Concepción, Chile;School of Computer Science, University of Windsor, Windsor, Canada N9B 3P4
Venue:
PRIB '09 Proceedings of the 4th IAPR International Conference on Pattern Recognition in Bioinformatics
Year:
2009

Citing 6
Cited 0

Seeded Region Growing

IEEE Transactions on Pattern Analysis and Machine Intelligence
Performance Evaluation of Some Clustering Algorithms and Validity Indices

IEEE Transactions on Pattern Analysis and Machine Intelligence
Measures of Similarity

WACV-MOTION '05 Proceedings of the Seventh IEEE Workshops on Application of Computer Vision (WACV/MOTION'05) - Volume 1 - Volume 01
Pattern Recognition, Third Edition

Pattern Recognition, Third Edition
Toward Objective Evaluation of Image Segmentation Algorithms

IEEE Transactions on Pattern Analysis and Machine Intelligence
An Efficient Algorithm for Optimal Multilevel Thresholding of Irregularly Sampled Histograms

SSPR & SPR '08 Proceedings of the 2008 Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

A microbial biofilm is structured mainly by a protective sticky matrix of extracellular polymeric substances. The appreciation of such structures is useful for the microbiologist and can be subjective to the observer. Thus, quantifying the underlying images in useful parameters by means of an objective image segmentation process helps substantially to reduce errors in quantification. This paper proposes an approach to segmentation of biofilm images using optimal multilevel thresholding and indices of clustering validity. A comparison of automatically segmented images with manual segmentation is done through different thresholding criteria, and clustering validity indices are used to find the correct number of thresholds, obtaining results similar to the segmentation done by an expert.