Machine vision detection and recognition of appear

  • Detail

Detection and identification of printing appearance defects by machine vision

in the printing process, due to process and other reasons, printing products often appear color difference, inaccurate overprinting, and some appearance defects such as defect points, ink lines, and black leather, resulting in the appearance of printing defects. Printing enterprises generally use manual methods to sort defective products by sampling in printing and visual inspection one by one after printing, which has low detection efficiency, high cost and high labor intensity. Practice has proved that using machine vision system to replace people to detect printing defects can improve production efficiency and reduce production costs. This paper discusses the use of PC based machine vision system to replace manual inspection of printed matter. Using the characteristics of high precision and fast speed of computer, it can quickly and accurately detect the appearance defects of printed matter, and comprehensively analyze the degree of defects, so as to judge whether the printed matter is inferior or scrap

I. image acquisition and preprocessing

the image acquisition card used in this system is Metro ii/mc of Matrox company, the CCD camera is pulnix6703, and the system image acquisition speed is set to 60 frames/second (image size is 640 × 480)。 The CPU of the microcomputer system is piii750 and the memory is 256M. The software development environment is Win98! VC6.0。

in the process of image acquisition, due to the influence of camera accuracy, lighting environment and other factors, the collected image will have a certain amount of random noise, resulting in image distortion. Here, a weighted median filtering algorithm is used, which can remove the sharp edge interference and maintain the edge details. Determine a window w with an odd number of pixels, first weight each pixel in the window, and the weighted value of a pixel is m, that is, the pixel repeats m when the gray level of the window pixels is queued, then arrange the pixels in the window according to the gray level value from large to small, and then replace the middle value of the original image f (x, y) with the gray level value in its middle position to obtain the enhanced image g (x, y)

II. Visual inspection

(I) defect detection

printing defects are reflected in the image, that is, the difference between the gray scale value at the defect of the collected image and the standard map. By subtracting the gray value of the collected image from the standard image (the pixel value is subtracted), and judging whether the difference (the difference degree of the gray value of the two images) exceeds the preset standard value range, we can judge whether the printed matter has defects

(II) defect recognition

after the difference is completed, a difference map with the same size as the collected map is obtained, and its pixel value is the difference of the corresponding pixel points of each two images. Then, the differential image is scanned line by line to detect the defect points. When the defective pixel is encountered (its value is 0), the whole defective area is traversed by recursive method, and the size and size of the defective area are recorded at the same time. After the whole scanning process is completed, the number of recursion is the number of defects. If the defect recognition is too bad, there will be two or more defect areas very close to each other (for example, two defect points have only one pixel distance on the image). They are usually considered to belong to the same defect area. Therefore, they need to be combined into a defect area before detection. Here is the expansion algorithm of mathematical morphology (as shown in Figure 1). After a series of operations such as corrosion, expansion and re corrosion, the edge shape of the defect image is extracted for further analysis and judgment. Multinational companies export technology and capital abroad

III. experimental results

the printed image collected in the static mode is tested. The experimental results show that (see Fig. 2, Fig. 3, FIG. 4, FIG. 5), the above method is effective, and the simulated defects can be completely detected, achieving the desired purpose

IV. discussion

using machine vision recognition system to replace manual print quality detection has practical value, which has been preliminarily discussed and attempted. The next step to be solved is dynamic image capture and processing, and the detection and recognition of defects such as color difference and inaccurate overprint, which are much more difficult than appearance defects. But at least 20mm. In addition, the evaluation of printing quality is a comprehensive index, and it is also very necessary to improve the intelligent information processing ability of the system

Lu Zhen Xie Yong

reprinted from: Packaging Engineering

Copyright © 2011 JIN SHI