Research On Flow White Blood Cell Images Classification Technology

To improve the correct recognition rate of white blood cells images, the effective methods of image denoising, image segmentation and feature extraction are studied in this article. In the image denoising process, we use the joint denoising method of the median filter and wavelet transform combine, salt and pepper noise and gaussian noise is very good inhibition in the white blood cell image. Because of the existence of grains in some type of white blood cells (granulocyte), the result of image segmentation is seriously affected. Integrating spatial information and kernel function into the fuzzy C-means clustering FCM algorithm, this paper proposes an improved FCM algorithm. Applying this new algorithm to image segmentation and taking the measure of mathematic morphology to process segmented image, the study gets a good segmentation effect and solves the problem of cytoplasm-nucleus of granulocyte segmentation. As for the feature extraction of cells, by fuzzification of the threshold parameter in local binary pattern (LBP), the texture feature extraction method based on local fussy pattern (LFP) is proposed. The employment of the methods above in image segmentation and texture extraction supports vector machine as the classifier and tests the classification of100CellAtlas’s white blood cells images. The results indicate that the correct recognition rate is up to93%.