Urinary Sediment Image Segmentation Based on Wavelet and Mathematical Morphology

A novel method is proposed to segment the defocused urinary sediment images based on wavelet transform and mathematical morphology. Since some particles of the image are very blurry, especially the inside and outside are very similar, first the images are segmented using wavelet transform and mathematical morphology, and then the coordinates of the subimages are obtained. Based on these coordinates, the corresponding threshold value are calculated, the subimages are segmented again respectively. The experimental results show that the method can effectively suppress the effect of defocusing and get the edge-blurry elements from the background precisely. The methods can be applied for the segmentation of further-ranging images.