The Applied Research On Image Processing Methods Of Bar Automatic Counting

Automatic count of the steel rods is a tough problem which has been puzzling producers for long time. At present, almost all steel factories count bundled steel rods by the manual and photoelectric cell counting methods, these two methods of steel bars’counting have many of limitations, are unable to satisfy the requirements of counting quickly and accurately. Therefore, developing a automatic counting system, which is able to automatically detect the number of the steel rods,seems urgently.In order to achieve this goal of steel bars’automatic counting, diagnostic engineering center on equipment in Northeastern University and FuShun steel Co. Ltd cooperated on the automatic counting system online for steel bars, while my thesis is the system’s image processing.This article serves the counting purpose through the recognition of the steel bars’ image, its main research content including image pretreatment, image division and pattern recognition. In the part of image pretreatment, this paper focuses on the linear transformation, gray stretch, image smooth, medianfilter, pseudo-color image etc. methods. The purpose is to get rid of the interference of background noise,get more ideal steel bars’image, prepare for the next image division. In the part of image division, used the two mothods of border partition and the threshold segmentation, bars’image is separated into two parts, the target and background. Multi-threshold segmentation is introduced, divides the bars’image into several parts, and get segmentation of each part. For the bars’image whose gray level is uneven,better result can be gotten by using this method. In the image recognition counting part, firstly,dealing the bars’image with mathematical morphology to eliminate conglutination of different bars’,then doing distance transformation to the processed binary images, at this time,you can get the cores of all regions, search on these core spots again and achieve the bar count at last.In addition, this paper analyse the factors that affect the counting accuracy,find out the background noise which bring in a great interference in the image processing, and propose some improvement advice.