Research Of The Inspection On The Electronic Button Surface Defects

Electronic button is the basic part in electronic product, motility and service life depend on the quality of electronic button. It is very important issue for detection surface defect of electronic button. An automatic measurement system was researched with vision, image processing and pattern recognition technology. The main content of this dissertation includes the following parts:1. The whole design scheme and the main module of detection mechanism were described in detail, analyzed the hardware performance and developed the motion vision experimental platform for electronic button surface defect detection.2. The image preprocessing technologies is researched. Using image preprocessing based on Laplacian sharpen algorithm to make the edge of the electronic buttons bright, in order to extract edge, image segmentation, the target area identification and regional shape extract etc. The experimental results indicated that the preprocessing based on Laplacian sharpen algorithm is ideal for enhancing the edge of electronic button.3. The theory and technology of image segmentation are studied. On analyzing the histogram of the electronic button, this dissertation uses image segmentation based on maximum between-cluster variance algorithm. The experimental results indicate that the segmentation is ideal for the defect of electronic button.4. In the research of feature extraction, this dissertation fetches out the gray, gray variance and the perimeter of feet which can express the character of electronic button based on analyzing the characteristics of electronic button surface image.This dissertation designs and develops an experimenting testing system based on image technology using Visual C++ 6.0 to identify defects of electronic button. The system consists of image processing algorithm, image segmentation, defect property extraction and identification of defects. The detection rate of the electronic buttons in experiments is up to 100%.