Research And Implementation On Counting System For Quasi-circle Objects Under Complicated Working Conditions

Automatic counting of quasi-circle objects such as the steel pipes and rods is the last process in assembly lines.At present,the count of the steel rods online is implemented by manual.This method,however,is labor-consuming,inefficient and limited in systematic producing capability,at the same time,it is also difficult to ensure the counting accuracy.Thus,an automatic counting system that could automatically detect the number of the steel rods is developed by this paper,which will raise productivity effectively,as well as making the stage of counting achieve automation in operation.An automatic counting system for quasi-circle objects under complicated working conditions is developed in this paper,based on computer vision,image processing,and pattern recognition,which includes the choice of system scheme,the designing of software and hardware,the analysis of algorithm and so on.The major aspects of this paper is as follows:First,related fields of digital image processing technology,and the specific applications of this technology to count the steel rods are briefly introduced.After analysing advantages and disadvantages of existing counting algorithm,the improved scheme is raisedSecond,an automatic counting system's general structure is designed,and specific solutions for the hardware part are put forward, including lighting system,camera system,image acquisition card and industrial computer.Third,an image processing software platform for the automatic counting system is put forth based on VC and OpenCV,which involves three modules:image pre-processing,automatic segmentation and counting.Based on a lot of technical literature,images of the steel rods collected real-timely are pretreated,including graying,region of interesting exacting,smoothing and binarization.Then,a new method is proposed,combining with modified rods adhesion automatic segmentation algorithm and counting quasi-circle objects based on region growing algorithm and mark line algorithm.It improves the higher accuracy and efficiency of counting quasi-circle objects.At last,the prototype system is built and images of the steel rods are recognized by presenting the counting way for quasi-circle objects in this paper.Emluator results show that the automatic counting system can count the number of the steel rods accurately and work well.