中文摘要：

提出了一种基于计算机图像处理与人工智能的人体外周血液白细胞分类算法.针对五类白细胞的细胞核和细胞质的特性,在常用的核质比和圆形度特征的基础上,提取其在纹理和形态学等方面的旋转不变共生局部二值模式特征和细胞核形状特征,并对上述特征进行组合及归一化处理,最后选取高效的随机森林作为上述特征的分类器.实验结果表明,所提的白细胞分类算法要比现有的几种分类方法具有更好的识别效果.

英文摘要：

A classification algorithm was put forward for human peripheral white blood cells （WBCs） based on computer image processing and artificial intelligence. According to the characteristics of the nucleus and the cytoplasm of five types of WBC, the pairwise rotation invariant co-occurrence local binary pattern feature on texture and the integral invariant shape feature on morphology were extracted from segmented cell images besides the usual nuclear-cytoplasmic ratio and circularity features. Then all these features were combined and normalized. Lastly a random forest was selected as an efficient classifier to classify those five types of WBC. Eexperiments show that the proposed classification algorithm has a better recognition accuracy than some other existing classification methods for WBCs.