The defects recognition of wheel tread based on linear CCD

In this paper, a defect detecting system of wheel tread based on linear charge coupled device (CCD) is established, and the image recognition technology of wheel tread defects under this system is studied. Firstly, images of the whole wheel tread are captured through the system. Secondly, median filtering and image contrast enhancement are processed on the defect images, and then the canny edge detection based on gradient histogram is performed. Thirdly, the images after edge detection are used for eight-neighbor boundary tracking, in order to obtain the sizes in-pixel of defects. Finally, the linear CCD camera is calibrated by Zhang checkerboard-like calibration method, and the actual sizes of defects are calculated. The results of this experiment show that the detecting system can identify the wheel tread defects effectively, and obtain the defects´ actual width and height accurately through image processing algorithm.