Research On Appearance Detection Technology Of Seal Based On Machine Vision

Along with the application of seals in the market of industrial production becoming more and more widely, precision is demanded higher and higher, with the corresponding to the detection technology and equipment requirements also become very high. However, a lot of manufacturers also apply traditional manual visual to the precision testing at present, this kind of detection method is not only wasting of time and manpower, but also can not reach the demand of accuracy; but there are some manufacturers use the machine visual detection methods, In this paper, the detection technology of seals appearance has non-contac、online、 objective and true、automatic and other advantages, and it can effectively solve the detection problems of seals surface defect.This paper combined machine vision, image processing with pattern recognition. Aiming at defecting the existing defect of seal appearance surface. In this paper, the main research object is type O sealing ring, CCD-array camera as the core component of the system, and collect it in real time with combination structure light sources and photoelectric sensor. Based on the collected gray image, and did a thorough research in accordance with the image processing algorithms, then on this basis to complete the key technology research, which is appearance surface defects detection and recognition.Defects in the possible existence of area, the general scheme of seal defect identification system has been came out. To the image preprocessing, using median filter to eliminate the image noise, and the image quality is greatly improved. After analyzes the advantages and disadvantages of each edge detection operator, this paper choose a suitable operator. To the image threshold segmentation, using the threshold segmentation method for binary image processing, calculate the area and perimeter of the binary defect image, and with binary tree model identification base on the structure method statement to complete defect classification. Finally, a software of defect detection system for seals is developed with Visual C++6.0 platform, which can detect the hackneyed defects of the movement seals. When a defect is detected, the defect image is displayed. This software also can stores the defect images into computer and user-friendly, steadily and efficiently.