Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Recognition Performance Improvement of QR and Color Codes Posted on Curved Surfaces

곡면상에 부착된 QR 코드와 칼라 코드의 인식률 개선

  • Kim, Jin-soo (Department of Info. & Comm. Engineering, Hanbat National University)
  • Received : 2018.09.28
  • Accepted : 2018.10.21
  • Published : 2019.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Currently, due to the widespread use of a smartphone, QR codes allow users to access a variety of added services. However, the QR codes posted on curved surfaces tend to be non-uniformly illuminated and bring about the decline of recognition rate. So, in this paper, the block-adaptive binarization policy is adopted to find an optimal threshold appropriate for bimodal image like QR codes. For a large block, its histogram distribution is found to get an initial threshold and then the block is partitioned to reflect the local characteristics of small blocks. Also, morphological operation is applied to their neighboring boundary at the discontinuous at the QR code junction. This paper proposes an authentication method based on the color code, uniquely painted within QR code. Through a variety of practical experiments, it is shown that the proposed algorithm outperforms the conventional method in detecting QR code and also maintains good recognition rate up to 40 degrees on curved surfaces.

현재 스마트 폰의 대중적인 보급으로 QR코드는 다양한 부가 서비스를 가능하게 하고 있다. 그러나 곡면에 부착된 QR코드는 불균일한 조도로 인해 인식률 저하를 초래한다. 그래서 본 논문에서는 QR 코드와 같은 응용에 적합하도록 블록 적응적 이진화 방법을 도입하여 최적의 이진화 임계치를 구하는 방법을 도입한다. 즉, 큰 블록에 대해 히스토그램을 구하여 초기의 임계치를 구하고, 그 블록을 분할하여 히스토그램에 따른 블록의 특성이 반영된 세분화된 임계치를 구하는 방법으로 이진화를 수행한다. 또한, 모폴로지 연산을 도입하여 QR코드와 같은 이웃 화소들의 특징이 반영되도록 하는 방법으로 적용된다. 주어진 정품 칼라코드와 입력 코드를 다수의 방법으로 비교하여 정품을 구별하는 판별 방법을 제안한다. 다양한 실험을 통하여 QR코드를 검출함에 있어 제안한 방법은 기존의 방법보다 우수한 성능을 보임을 확인하며, 또한, 기존의 방식에 비해 40도까지의 높은 곡률에서도 우수한 인식률을 유지함을 보인다.

Keywords

HOJBC0_2019_v23n3_267_f0001.png 이미지

Fig. 1 Position detection pattern of QR code [1]

HOJBC0_2019_v23n3_267_f0002.png 이미지

Fig. 2 Uneven illumination caused by curvature (a) captured image (b) simple binarization result

HOJBC0_2019_v23n3_267_f0003.png 이미지

Fig. 3 The proposed binarization algorithm for QR code recognition.

HOJBC0_2019_v23n3_267_f0004.png 이미지

Fig. 4 Histogram of each section in the block. (a) top left of the block (b) top right of the block (c) bottom right of the block (d) bottom left of the block

HOJBC0_2019_v23n3_267_f0005.png 이미지

Fig. 5 The results of binarization (a) small block size (b) middle block size[2] (c) large block size[3] (d) proposed algorithm

HOJBC0_2019_v23n3_267_f0006.png 이미지

Fig. 6 Binarization image about part of QR code image (a) Xiong[2] (b) Michalak[3] (c) the proposed

HOJBC0_2019_v23n3_267_f0007.png 이미지

Fig. 7 The flow-chart of color code algorithm.

HOJBC0_2019_v23n3_267_f0008.png 이미지

Fig. 8 An Example of MAD density distribution

HOJBC0_2019_v23n3_267_f0009.png 이미지

Fig. 9 An Example of SSIM and Number of highly errored pixels.

HOJBC0_2019_v23n3_267_f0010.png 이미지

Fig. 10 Experimental images posted with QR and Color codes

HOJBC0_2019_v23n3_267_f0011.png 이미지

Fig. 11 Recognition rate for QR code (a) Xiong[2] (b) the proposed algorithm

HOJBC0_2019_v23n3_267_f0012.png 이미지

Fig. 12 Recognition rate for color code (a) recognition rate (b) unrecognized rate (c) incorrect recognition rate

References

  1. Keyence corp., Autofocus 1D and 2D Code Reader [Internet], Available: https://www.keyence.co.kr/.
  2. Z. Xiong, H. Cuiqun, L. Guodong, and L. Zhijun, "A binarization method of quick response code image," in 2015 2nd International Conference on Signal Processing Systems, Dalian : China, pp. V3-317-320, 2010.
  3. H. Michalak, and K. Okarma, "Region based adaptive binarization for optical character recognition purposes," in 2018 International Interdisciplinary PhD Workshop (IIPhDW), Swinoujscie : Poland, pp.361-366, 2018.
  4. Z. Liao, T. Huang, R. Wang, and X. Zhou, "A method of image analysis for QR code recognition," in 2010 International Conference on Intelligent Computing and Integrated Systems, Guilin : China, pp.250-253, 2010.
  5. W. Xuan, C. Peng, F. Liuping, Z. Jianle, and H. Peijun, "Research on correcting algorithm of QR code image's distortion," in 2017 IEEE 17th International Conference on Communication Technology (ICCT), Chengdu : China, pp. 1752-1756, 2017.
  6. Y. Gu, and W. Zhang, "QR code recognition based on image processing," in International Conference on Information Science and Technology, Nanjing : China, pp. 733-736, Mar. 2011.
  7. M. Ahn, S. Hong, and S. Lee, "A research of the QR code recognition improvement using the cloud-based pre-generated image matching scheme" in 2015 International Conference on Information Networking (ICOIN), Cambodia : Cambodia, pp. 356-357, 2015.
  8. D. Choi, and J. Kim, "A code authentication system of counterfeit printed image using multiple comparison measures," Journal of the Korea Industrial Information Systems Research, vol. 23, no. 4, pp. 1-12, Aug. 2018. https://doi.org/10.9723/JKSIIS.2018.23.4.001
  9. N. Arora, M. Martolia, and A. Ashok, "A Comparative study of the Image Registration Process on the Multimodal Medical Images," Asia-pacific Journal of Convergent Research Interchange, HSST, ISSN : 2508- 9080, vol. 3, no. 1, March (2017), pp. 1-17, http://dx.doi.org/10.21742/APJCRI.2017.03.01.
  10. J. Ryu, and J. Kim, "An effective MC-BCS-SPL algorithm and its performance comparison with respect to prediction structuring method," Journal of the Korea Institute of Information and Communication Engineering, vol. 21, no. 7, pp. 1355-1363, Jul. 2017. https://doi.org/10.6109/JKIICE.2017.21.7.1355
  11. Jung Hyun Kim, and Kirti Raj Bhatele, "Recognition using Cyber bullying in view of Semantic-Enhanced Minimized Auto-Encoder," Asia-pacific Journal of Convergent Research Interchange, HSST, ISSN : 2508-9080, vol.2, no.4, December (2016), pp. 7-14, http://dx.doi.org/10.21742/ APJCRI.2016.12.02.
  12. Jae-Gon Kim, and Jin-soo Kim, "Performance Improvement of Traffic Signal Lights Recognition Based on Adaptive Morphological Analysis," Journal of the Korea Institute of Information and Communication Engineering 19(9), 2015.9, 2129-2137. https://doi.org/10.6109/jkiice.2015.19.9.2129
  13. D. Choi, and J. Kim, "An effective detection of print image forgeries based on modeling of color matrix : an application to QR code ," The Journal of the Korea Contents Association, vol. 18, no. 10, pp. 431-442, 2018. https://doi.org/10.5392/JKCA.2018.18.10.431

Cited by

  1. 오프라인 응용을 위한 컬러 QR코드의 삽입 정보 추출 방법 vol.24, pp.9, 2019, https://doi.org/10.6109/jkiice.2020.24.9.1123
  2. 색 및 패턴 정보 다중화를 이용한 칼라 QR코드의 비트 인식률 개선 vol.24, pp.8, 2019, https://doi.org/10.9717/kmms.2021.24.8.1012