研究白细胞图像分类识别中有效的图像分割与特征提取方法,以提高白细胞图像的正确识别率。由于某些白细胞(粒细胞)中颗粒的存在,严重影响细胞核与细胞质区域的正确分割,通过将空间信息与核函数融入模糊C-均值聚类(FCM)算法,提出一种改进的FCM算法。应用该算法对白细胞图像进行分割,并采用数学形态学方法对分割后的图像进行处理,获得了很好的分割效果,解决了粒细胞的质核分割难题。对于细胞的纹理特征提取,通过对局部二值模式(LBP)中阈值参数的模糊化,建立了基于局部模糊模式(LFP)的纹理特征提取算法。运用本文方法进行图像分割和纹理提取,以支持向量机作为分类器,对CellAtlas的100幅白细胞图像进行了分类识别的实验,结果表明白细胞的正确识别率达到93%。

To improve the correct recognition rate of white blood cells images, the effective methods of image segmentation and feature extraction are studied in this article. 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 of 100 CellAtlas's white blood cells images. The results indicate that the correct recognition rate is up to 93%.