一种有效的白细胞图像彩色空间序贯分割方法

Sequential Segmentation of Leukocyte Image with Color Parameters

为解决血液白细胞显微图像自动识别中的图像分割问题，文中提出了一种在彩色空间内，先采用自动阈值分割技术扣除背景，得到白细胞核区域模板；然后用以色调相似性作为增长准则，以白细胞形状的凸出形态作为收敛准则，序贯分割白细胞浆区域的处理方法．大量实验表明，该方法能稳定、有效地分割出白细胞区域．

The problem of image segmentation for automatic recognition of leukocyte image is solved by using the color parameters. Segmatation of leukocyte is accomplished by first applying the threasholding method to segment the nuclear and background region and then use is made of region expanding method with the aggregation criterion based on color similarity and convexity criteria. Feasibility of this approach is validated by experiments.