Grid-Based Genetic Algorithm Approach to Colour Image Segmentation

Image segmentation is a crucial problem in image processing and can determine the final outcome of many image processing tasks. A great deal of research has gone into segmentation of monotone images, however, only recently has research gone into segmenting colour images. Genetic algorithms have been shown to be a viable method to segment an image. However, little research has gone into developing a parallel genetic algorithm for a Grid computing environment, which consists of heterogeneous, non-dedicated resources. This paper surveys some of the existing segmentation techniques that have been developed in search of which work best. Existing parallel genetic algorithm models are adapted for the Grid and the results from the segmentation experimentation are used in producing a Grid-based genetic algorithm solution for colour image segmentation. The results show that the Watershed Transformation produces effective segmentation results. Other segmentation techniques evaluated are both less efficient and produce lower quality segmentations. The genetic algorithm solution improves results, while the resource-intensive algorithms benefit from the additional resources available on the Grid. The Grid-based genetic algorithm model is shown to be effective. While still requiring further development, the results are positive. CR Categories: I.4.6 [Image Processing and Computer Vision]: Segmentation – Edge and feature detection; Region growing, partitioning