The invention discloses a white blood cell segmentation method based on super pixels and an anomaly detection color blood cell image. The method includes the steps that firstly, CMYK and HIS color space of an original color blood cell RGB image is combined with image airspace information, a seven-dimension feature vector is established, an image is pre-segmented by an SLIC superpixel partitioning algorithm, and a superpixel segmentation image is obtained; secondly, a cell nucleus area is detected by using an abnormal target detection method, an abnormal energy value image of each pixel point is obtained, and a pre-segmented cell nucleus area image is obtained after area smoothing and threshold segmentation are conducted; finally, corresponding superpixel areas of the pre-segmented cell nucleus area image and the superpixel segmentation image are combined, as for H component of white blood cell HSI space, surrounding pixel points of a cell nucleus are selected to serve as seed points to conduct area growing, the surrounding pixel points are combined with a pre-segmented superpixel image, and white blood cells are segmented out. The segmentation algorithm is simple, the segmentation speed is high, part space information is adopted during segmenting, and the segmentation is more accurate.