A Novel Parallel Swarm Approach for Cell Image Segmentation

In this paper, we propose a novel parallel particle swarm optimization approach for segmentation of extremely noisy cell images. In this approach the roblem dependent knowledge about cell shape is taken into account. To this end, an elliptical model of cell contour is incorporated into this model which shows etter detection of cell boundary. First by using Canny edge detector the gradient image is produced. Then a kernel based dynamic clustering algorithm is employed to specify the image points with high probability of belonging to each cell. Finally a parallel particle swarm optimization algorithm is used to adjust the parameters of the cell contour model to find the best matching. The segmentation results on the benchmark images of noisy human thyroid and small intestine cell images demonstrate that the proposed method is very successful in segmenting images of elliptically shaped cells.

Keywords:

Parallel particle swarm optimization , Noisy image , Cell image segmentation , kernel based dynamic clustering , Elliptical cell contour