Research On The Detection Technology Of Medical Microscopic Cell Based On Hough Transform

Stool examination is a routine clinical examination, and has always been the traditional checks of hospitals, and is of great significance for the diagnosis and treatment of digestive tract diseases and discrimination.With the widespread development and application of image processing and recognition technology in the biomedical field, microscope inspection also gradually transition from manual method to automatic analysis. In recent years, the automatic detection system has become a new research hot spot in biomedical field, the use of high performance computers in a substantial increase in the image processing speed, but also greatly shortens the time of clinical pathology on judgment. Automated microscopy system can generally be divided into processes such as image acquisition, image processing and recognition. Paper on stool microscopy image segmentation method for in-depth study. According to characteristics of complex background, more interference and cell shape mostly round in shape,firstly, the edge detection of cell image segmentation, and then to the location and extraction of target cells by Hough transform. Main research work and results achieved include:(1) Studied several kinds of commonly used classical edge detection operators, briefly introduces the detection principle of them, according to the results of simulation experiment, analyzed and compared their advantages and disadvantages. Focus on the preliminary segmentation method of stool microscopy cell image based on Canny edge detection algorithm, aiming at disadvantages of traditional Canny edge detection algorithm, research on the corresponding improved algorithm, such as image pixel classification, threshold segmentation of histogram concavity, anisotropic diffusion filtering, adaptive edge detection and so on. In this paper, adaptive Canny detection algorithm is proposed.(2) Study on the basic principle and application of the Hough transform, using Hough transform algorithm as extraction and location method of stool microscopic cell image, study the correlation of Hough transform and its improvement methods for the detection of microscope image kind of round cell, such as the SHT detection algorithm, improved algorithm based on geometric feature dimension reduction and so on. Analysis and discuss the drawbacks of Hough algorithm in practical application, combined with the elliptic parameter equation, and put forward the "two step" Hough transform ellipse detection algorithm.