尿沉渣图像中红白细胞的分割和识别.pdf

Subject : Segmentation and Recognition of Red Cells and White Cells in Urinary Sediment Images Specialty : Signal and information processing Name : ZhaoShaohua (Signature) Instructor : WuYanhai (Signature) ABSTRACT Urinary sediment inspection refers to the inspection of pathologica l components in urinary. Through analysis of the components, such as red cells, white cells, epithelial cells and cast cells, test whether there is some disease or injury in the kidney and urinary system. As a common and important clinical test, urinary sediment inspection is significant to clinical diagnosis, treatment detection and health screening. In this paper, combined with the characteristics of urinary sediment images, several effective segmentation and recognition algorithms are proposed by using digital image processing and pattern recognition techniques to recognize the particles in the urinary sediment, both in theory study and practice. In the urinary sediment preprocessing, anisotropic gauss filtering method is applied. Compared with traditional filter methods, the method denoises images and protects edge information simultaneously. In image segmentation, three combinational segmentation algorithm is proposed. Adaptive Canny edge detection is utilized in top layer, Otsu threshold segmentation in the middle, and segmentation based on gradient in the bottom, eventually get complete segmentation result by merging each layer ’s result. For overlapping cells in the segmentation result, a new algorithm based on recursive bottleneck is proposed in this paper. It locate the bottleneck points by b