Image segmentation using Watershed Transform and Ant Colony Optimization

• Grant number: 11/15578-2
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: October 01, 2011
• End date: May 31, 2012
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Marco Antonio Garcia de Carvalho
• Grantee: Diego de Souza Silva
• Host Institution: Faculdade de Tecnologia (FT). Universidade Estadual de Campinas (UNICAMP). Limeira , SP, Brazil

Abstract

Image segmentation is a commom task on Digital Image Processing. Basically, the goal is subdividing an image into its constituent parts. One recent approach of image segmentation is to apply bio-inspired algorithms, in other words, algorithms built from the observation of natural phenomena. This area is known as Natural Computing. In this work, we use an algorithm known as Ant Colony Algorithm in order to segment digital images. The image model will be obtained by means of graphs, generated from Watershed Transform, where primitive regions corresponds to the nodes and edges indicate relations between regions. Moreover, ee use weighted graphs.It is intended in this work to implement image segmentation of digital images of microscopic cells. We hope that this model provides a good segmentation for the given application. The results will be compared with those produced by other techniques of image segmentation.