DOI QR코드

DOI QR Code

A Morphology Technique-Based Boundary Detection in a Two-Dimensional QR Code

2차원 QR코드에서 모폴로지 기반의 경계선 검출 방법

  • 박광욱 (충북대학교 컴퓨터교육과) ;
  • 이종연 (충북대학교 소프트웨어학과)
  • Received : 2014.12.15
  • Accepted : 2015.02.20
  • Published : 2015.02.28

Abstract

The two-dimensional QR code has advantages such as directional nature, enough data storage capacity, ability of error correction, and ability of data restoration. There are two major issues like speed and correctiveness of recognition in the two-dimensional QR code. Therefore, this paper proposes a morphology-based algorithm of detecting the interest region of a barcode. Our research contents can be summarized as follows. First, the interest region of a barcode image was detected by close operations in morphology. Second, after that, the boundary of the barcode are detected by intersecting four cross line outside in a code. Three, the projected image is then rectified into a two-dimensional barcode in a square shape by the reverse-perspective transform. In result, it shows that our detection and recognition rates for the barcode image is also 97.20% and 94.80%, respectively and that outperforms than previous methods in various illumination and distorted image environments.

2차원 QR 코드는 1차원 바코드의 데이터 용량 문제를 극복하였고, 방향성, 오류 정정, 데이터 복원력 등의 장점이 있다. 특히 2차원 바코드 인식에서 주요 이슈는 인식 속도와 정확성이다. 따라서 본 논문에서는 바코드 영역을 검출하기 위한 알고리즘을 제안하며, 제안 방법은 영상 내 관심 영역의 위치를 검출하기 위해 모폴로지 기법을 기반으로 한다. 세부적인 연구내용은 다음과 같다. 첫째, 모폴로지 닫힘(close) 연산을 통해 입력 이미지에서 QR Code의 바코드 영역을 검출한다. 둘째, 경계선 검출을 통해 바코드 영역의 외곽선들을 검출한다. 셋째, 검출된 네 개의 외곽 교차점인 네 점을 추출한 후 역 투시변환을 통하여 2차원 바코드의 정사각형 모양으로 정규화 한다. 결과적으로 본 논문의 연구결과는 다양한 조명상태이나 영상에 강한 왜곡이 있는 경우에도 좋은 성능을 나타내며, 영역 검출율은 94.8%, 인식률은 92.3%로 기존연구들보다 안정된 바코드 검출 및 인식 성능을 보여주고 있다.

Keywords

References

  1. GS1, GS1 General Specifications Version 13, 2013
  2. Thonky, QR Code. http://www.thonky.com/qr-code-tutorial/. (2013)
  3. wikipedia, QR code, http://en.wikipedia.org/wiki/QR_code. (2013)
  4. ISO/IEC 1804:2000, Information technology: Automatic identification and data capture techniques - Bar code symbology - QR Code, 2000
  5. Ani1 K. Jain, and Yao Chen, BarCode Localization Using Texture Analysis. Document Analysis and Recognition, pp41-44, 1993.
  6. Ruben Mufiiz, and Luis Junco, and Adolfo Otero, A Robust Software Barcode Reader Using the Hough Transform. 1999 International Conference on Information Intelligence and Systems, pp 313-319, 1999.
  7. Seung-Jin Kim, and Yoon-Su Jung, and Bong-Seok Kim, and Jong-Un Won, and Chul-ho Won, and Jin-Ho Cho, and Kuhn-Il Lee, Bar Code Location Algorithm Using Pixel Gradient and Labeling. The KIPS transactions, Part D, Vol. 10D, No. 7, pp. 1171-1176, 2003. https://doi.org/10.3745/KIPSTD.2003.10D.7.1171
  8. Moon-Sung Park, and Jin-suk Kim, and Hye-Kyu Kim, and Hoe-Kyung Jung, A Study on High-Speed Extraction of Bar Code Region for Parcel Automatic Identification. The KIPS transactions, Part D, Vol. 9D, No. 5, pp. 915-924, 2002. https://doi.org/10.3745/KIPSTD.2002.9D.5.915
  9. Normand, Nicolas, and Christian Viard-Gaudin. A two-dimensional bar code reader. Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol.3, pp. 201-203, 1994.
  10. Sang-Hyup Lee, and Kyoung-Mu Lee, Feature Extraction in Document Images Using Morphological. Proceedings of the Korean Society of Broadcast Engineers Conference, pp. 67-75, 1996.
  11. Mi-Young Park, and Chul-Won Kim, and Jong-Hoon Park, A Study on Canny Edge Detector Design Based on Image Fuzzification. Korea Institute of Information and Communication Engineering, Vol. 15, No. 9, pp. 1925-1931, 2011. https://doi.org/10.6109/jkiice.2011.15.9.1925
  12. Wolberg, George. Geometric transformation techniques for digital images: a survey. 1988.
  13. wikipedia, Perspective(graphical), http://en.wikipedia.org/wiki/Perspective_(graphical).
  14. DOI: http://math.stackexchange.com/questions/96662/augmented-reality-transformation-matrix-optimization.
  15. Google, Zxing, http://code.google.com/p/zxing. (2013)