Research, Medical Image Edge Detection Algorithm Based On Three-dimensional Reconstruction Of Human Information

Image edge detection is the foundation of feature extraction, Edge, an important feature of images, has received wide attention of many researchers in the fields, such as medical image, computer vision, pattern recognition and moving target detection. Aiming at the research item about 3D rebuilding and visualization of body information system, the author discusses the technique of medical image edge detection emphatically. Firstly, this paper describes the research course and application of body information system;then, the research background, present situation and research results, both domestic and abroad, of the edge detection are surveyed systematically and comprehensively. Canny has proposed three continuous criteria to compare the performance of different filters: good detection, good localization and low-responses. Based on these criteria he got optimal filter for edge detection: derivative of Gaussian function. After more than ten years research, Canny's theory has been ameliorated in many aspects, Which is also reviewed in this paper. Demigny gave three discrete criteria for edge detection like Canny's criteria, and he has proofed that the third criterion can be replaced by an appropriate threshold operation. This paper used numerical method to get the optimal filter and smooth operator under the Demigny's criteria, The author combine these filers and Canny's edge detecting technique to get an integrated edge detecting algorithm, and implement the algorithm. From the results of the program for many images, This filter and algorithm are not only simple, but also effective. So it is a practical method of edge detection.Finally, the author reviews the whole work. The experience and the future prospects in research of edge detection are presented at the end. Some subjects for further research are presented.