Direct Part Mark Bar Code Image Preprocessing

Due to factors such as ambient light and metal materials, the collected industrial DPM bar code images may exist uneven illumination, low contrast, color of background area is darker than bar code region and other harsh issues, while the existing 2D code recognition device can only recognize the type which bar code area color is darker than background region. Therefore, the quality of preprocessing effect is the key point to subsequent recognition algorithm. In this paper, the homomorphic filtering method is used to weaken the influence of uneven illumination firstly, which will enhance the image contrast degree. Then do horizontal and vertical projection, find the points with greater intensity changes in both directions, make the image into blocks, again use the classic Kittler binarization algorithm on each block, then use mathematical morphology method to standardize the dot data matrix images. Finally, an improved Hough transform method is used to detect the 'L' type finder pattern accurately, then find its pixel value, if color of the background region is darker than the bar code area, do invert-color processing. The processing results of a set of industrial DPM bar code images confirm the effectiveness of the proposed method.