Image segmentation for somatic cell of milk based on niching particle swarm optimization Otsu

Abstract

Aiming at the issue that it is easy to cause visual fatigue to count the quantity of milk somatic cells by microscope artificially, this paper raised automatic detection methods of counting milk somatic cells. To improve the quality of milk somatic cell's image, filtering and strengthening images with the method of DFT (Discrete Fourier Transformation). In order to increase the accuracy and speed of segmentation for somatic cell of milk images, and adjust the rapid testing requirement, it came up with the optimal threshold of image segmentation method based on niching particle swarm optimization Otsu(maximum class square error method). This method overcame the disadvantage of easily trapping in local solution and low rate in later convergence, improved the global optimization ability of the algorithmic. Using niche particle swarm optimization to optimize fitness function, it got the best segmentation threshold of Otsu, which could be used for image segmentation. At last, this paper provided handling methods for cell overlap and adhesion, through segmentation experiments using three different kinds of images of dyed milk somatic cell. Experiments showed that the methods raised in this paper are workable.