On-line Detection for LED Module Based on Machine Vision

LED module board is the basic composition unit of LED panel, and the quality of module board is the key and premised for panel to obtain a display of good quality. In this paper, based on the practice of project, use median filtering to filter the pulse and salt-pepper noises, which are produced in the process of image acquisition, and use the adaptive OTSU to segment images, adjust the angle between standard position image and the image caused by table vibration with Fomier-Mellin method, and process results adjusted with bilinear interpolation method. Results show that, using the image segmentation method can accurately determine the threshold image segmentation, results meet factory detection requirements, the method can be used in the industrial field of application of real-time measurement system with a higher promotional value.