DOI QR코드

DOI QR Code

2D 바코드의 분진 오염 극복 방법

A Method to Recover 2D barcodes Contaminated with Dust

  • Ha, Eunjae (Department of Electronic Engineering, Korea National University of Transportation) ;
  • Lee, Jaesung (Department of Electronic Engineering, Korea National University of Transportation)
  • 투고 : 2018.12.13
  • 심사 : 2019.01.09
  • 발행 : 2019.03.31

초록

푸드 프린터는 반드시 식품의약품안전처의 허가를 받은 식용 잉크 카트리지를 사용해야한다. 잉크 카트리지의 정품 여부를 판독하기 위해 2D 바코드를 사용하는데 색소가 열압력에 의해 발산하여 인쇄가 되기 때문에 바코드에 오염이 발생한다. 본 논문에서는 라떼 아트 프린터에서 식용 색소 분진에 의한 정품 인증 바코드의 오염 문제를 해결하고자 다양한 모폴로지 연산에 기반한 전처리(pre-processing) 알고리즘을 제안하였다. 오염된 바코드 이미지들을 QR코드 리더기로 인식시키기 전에 본 알고리즘을 적용하면 기존의 리더기 대비 인식이 가능한 오염도가 25%에서 40%로 증가함을 알 수 있었으며 45%의 오염도에서도 50%의 확률로 인식이 되는 것을 확인하였다.

Food printers must use food ink cartridges approved by the Ministry of Food and Drug Safety (MFDS). A 2D bar code is used to read whether the ink cartridge is authentic. However, since the dye is diverged by heat pressure and printed, the barcode is contaminated. In this paper, we propose a pre-processing algorithm to solve the problem of barcode contamination by food coloring dust in a latte art printer. The algorithm is based on various morphological operations. We apply this algorithm before reading contaminated barcode images with a general QR code reader. It has been confirmed that, as compared with the existing QR code reader, the contamination rate that can be perceived is increased from 25% to 40% and even at a contamination rate of 45%, the recognition rate reaches 50%.

키워드

HOJBC0_2019_v23n3_276_f0001.png 이미지

Fig. 1 Latte art printer and latte sample

HOJBC0_2019_v23n3_276_f0002.png 이미지

Fig. 2 Processing flow of the algorithm

HOJBC0_2019_v23n3_276_f0003.png 이미지

Fig. 3 Barcode images at each processing stage (a) Barcode image with 40% coloring dust (b) After converting Fig. 3(a) into a gray image and applying the Gray CLOSING operation twice to remove pepper noises (c) After applying THRESHOLD to the noise-free image and set Max_Value to pixels less than the threshold value and set 0 to pixels more than the value (d~e) Images obtained by dilating Fig. 3(c) one to two times, respectively (f~k) The results of applying the erode erosion operation to Fig. 3(e) 1 to 6 times, respectively

HOJBC0_2019_v23n3_276_f0004.png 이미지

Fig. 4 Performance evaluation for recognition rate

HOJBC0_2019_v23n3_276_f0005.png 이미지

Fig. 5 Experimental environment

참고문헌

  1. T. Kim, and E. Kim, "Vehicle license plate recognition system using morphological ROI (region of interest) map generated from morphology operation," Journal of Physics: Conference Series, vol. 806, no. 12004, pp. 1-6, Feb. 2017.
  2. Y. J. Kim, and J. Y. Lee, "Algorithm of a Perspective Transform-based Recognition in a PDF417 Barcode," Wireless Personal Communications, vol. 89, iss. 3, pp. 893-911, Aug. 2016. https://doi.org/10.1007/s11277-016-3171-6
  3. OpenCV team. Open Source Computer Vision Library [Internet]. Available: https://docs.opencv.org/master/d9/df8/tutorial_root.html.
  4. N. A. Rathod, and S. A. Ladhake, "Detecting and Decoding Algorithm for 2D Barcode," International Journal of Emerging Technology and Advanced Engineering, vol. 2, iss. 11, pp. 199-202, Nov. 2012.
  5. C.-Y. Lee, and N.-H. Kim, "A Study on Mask-based Edge Detection Algorithm using Morphology," Journal of the korea Institute of Information and Communication Engineering, vol. 19, no. 10, pp. 2441-2449, Oct. 2015. https://doi.org/10.6109/jkiice.2015.19.10.2441
  6. P. Bodnar, and L. G. Nyul, "Barcode detection with morphological operations and clustering," in Proceedings of the IASTED International Conference on Signal Processing, Pattern Recognition and Applications, Crete, Greece, pp. 51-57, 2012.
  7. SourceForge. ZBar bar code reader [Internet]. Available: http://zbar.sourceforge.net.
  8. J. Song, and J. Lee, "Positioning Method Using a Vehicular Black-Box Camera and a 2D Barcode in an Indoor Parking Lot," Journal of the Korea Institute of Information and Communication Engineering, vol. 20, no. 1, pp. 142-152, Jan. 2016. https://doi.org/10.6109/jkiice.2016.20.1.142
  9. J.-H. Huh, "Designing of Image Processing Curriculum Considering Network Security," Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, vol.7, no.6, pp. 861-869, June 2017. https://doi.org/10.35873/AJMAHS.2017.7.6.081