The invention discloses an on-line defect detection
system and method for thin bamboo strips based on
machine vision. The on-line defect detection
system comprises an industrial
personal computer, a PLC, an
air pump, two electromagnetic valves, two air knives, an isolation board, a line-array camera, an area-array camera, two motors, two narrow conveyor belts and four photoelectric sensors, wherein the conveyor belts convey thin bamboo strips to the area-array camera and the line-array camera; front side and reverse side images of thin bamboo strips are collected, and the images are input into the industrial
personal computer for image pretreatment; profile and surface defects are detected, so as to obtain three types of products, namely products with profile defects, products with surface defects and products without defects; the
classification result is output to the PLC through a
serial port, and the electromagnetic valves are controlled to be opened through the PLC, and products with profile defects and surface defects are removed; if no defect is detected, the PLC fails to actuate. According to the on-line defect detection
system and method for thin bamboo strips based on
machine vision, the problems of missing defection and
false detection in manual detection are avoided, and the detection accuracy is improved; moreover, historical data is stored by utilizing a
database, the querying is convenient, and the counting is accurate; and besides, the system has a clear structure and is simple in operation.