Mumford-Shah Segmentation for Microscopic Image of the Urinary Sediment

The technology of computer image processing has been widely used in the microscopic examination of the urine sediment. Image segmentation and contour detection is important for computer vision and pattern recognition, and the active contour segmentation for microscopic cell image of the urinary sediment is treated as the most popular study focus. This paper introduced the segmentation model based on Mumford-Shah. We developed the corresponding Euler-Lagrange equation by Gateaux derivative method. And a new algorithm of level set method is constructed by additive operator splitting (AOS) scheme to the microscopic image in urinary automation analysis. The experimental results show that the proposed algorithm is efficient, stable, and convergent and has great application value for automation detection of microscopic image.