Research Of Image Process Methods Focusing In Counting System Of Steel-bar

Base on the purpose of automatically counting out the number of a bundle of Steel-bar by means of digital image process, this paper is mainly research the relevant image process methods. The main contents of this paper contains three parts, first part introduce how to build up such Image Sample & Dispose System and the flow of its work step; then give the improved methods of segmentation and morphology in such system; discuss the research of target ladling and counting methods.This paper introduces the method of getting image through USB camera, and describes the software flow of image process, target recognize and real-time counting.This paper mainly researches the application and improvement of methods about image process, such as image segmentation, morphological dispose. Introduce two methods of segmentation, which are named 2D-threshold segmentation and multi-threshold segmentation based on maximum between-class variance is suggested in this paper. Two-dimension threshold segmentation method takes both gray level of point and area into account, and analysis the reason of the gray level's change, improve the criterion of segmentation, then make the result of segmentation better; multi-threshold segmentation divides a image into several parts, and get segmentation of each part, then integrate the results by estimating the comparison of each threshold with global threshold. For the image whose gray level is uneven, better result can be gotten by using this method.Base on the shape of steel-bar and memory feature of binary image, give a new method named mean-value morphology, which is derived from smoothing spatial technology and mathematic morphology. By using this method, the system can adaptively do operation of erosion or expansion to each target area after image segmentation at same time, such as erode edge area of target, and expand target area where it is adjacent to a small hole which is generated by improper segmentation. Base on the morphological feature of different patterns, the method can automatically process image morphology disposal with different direction and speed.An improved arithmetic to get better result after segmentation, and morphology dispose. MorphologyExperiments indicate that the methods mentioned in this paper have real-time performance and accuracy, and have a good application value.