Precise Localization of PDF417 Code Based on Fast Hough Transform

Dmitrii G. Mitrofanov, Pavel K. Zlobin, Julia A. Shemiakina, Pavel V. Bezmaternykh

Аннотация


The PDF417 is a popular barcode symbology which is widely used in a huge variety of business processes. In this paper, we propose an original method for precise PDF417 code localization. It can successfully process projectively distorted images captured via the mobile device cameras. The core of this method is the analysis of the Fast Hough Transform image. This analysis is aimed to: (a) determine the line, corresponding to the vanish point of vertical symbol sides, using the RANSAC algorithm; (b) select the best pair of Hough-points corresponding to the horizontal symbol sides. We also propose the evaluation methodology for assessing the accuracy of precise PDF417 localization and a new dataset SE-PDF417-SYN-400, which consists of 400 synthesized PDF417 images and is publicly available. The accuracy of the proposed method on SE-PDF417-SYN-400 is equal to 0.948, and its error rate is about four times less than the one obtained by the popular ZXing detector. The average running times on iPhone 8 and iPhone 14 Pro Max mobile devices are equal to 77 and 34 ms per image correspondingly.

Ключевые слова


barcode reading; PDF417; Fast Hough Transform; vanish point; RANSAC

Полный текст:

PDF (English)

Литература


Information technology — Automatic identification and data capture techniques — PDF417 bar code symbology specification: Standard / International Organization for Standardization. 2015. DOI: 10.1007/978-981-19-0386-1_49.

Chen C., Kot A.C., Yang H. A two-stage quality measure for mobile phone captured 2D barcode images. Pattern Recognition. 2013. Vol. 46, no. 9. P. 2588–2598. DOI: 10.1016/j.patcog.2013.01.031.

Wudhikarn R., Charoenkwan P., Malang K. Deep Learning in Barcode Recognition: A Systematic Literature Review. IEEE Access. 2022. Vol. 10. P. 8049–8072. DOI: 10.1109/access.2022.3143033.

Ginkel M. van, Hendriks C.L., Vliet L.J. van A short introduction to the Radon and Hough transforms and how they relate to each other. Quantitative Imaging Group, Imaging Science & Technology Department, TU Delft. 2004. P. 1–9.

Aliev M., Ershov E., Nikolaev D. On the use of FHT, its modification for practical applications and the structure of Hough image. The Proceedings SPIE. The 11th International Conference on Machine Vision (ICMV), Munich, Germany, November 1–3, 2018. Vol. 11041. 2019. DOI: 10.1117/12.2522803.

Gaur P., Tiwari S. Recognition of 2D Barcode Images Using Edge Detection and Morphological Operation. International Journal of Computer Science and Mobile Computing. 2014. Vol. 3, no. 4. P. 1277–1282.

Liu F., Yin J., Li K., Liu Q. An improved recognition method of PDF417 barcode. Chinese Conference on Pattern Recognition (CCPR), Chongqing, China, October 21–23, 2010. IEEE. 2010. P. 1–5. DOI: 10.1109/CCPR.2010.5659332.

Kim Y.J., Lee J.Y. Algorithm of a Perspective Transform-Based PDF417 Barcode Recognition. Wireless Personal Communications. 2016. Vol. 89, no. 3. P. 893–911. DOI: 10.1007/s11277-016-3171-6.

Xiao Y., Yi J., Qiao G. Automatic Localization of Multi-type Barcodes in High-Resolution Images. International Conference in Communications, Signal Processing, and Systems (CSPS), Changbaishan, China, July 23–24, 2021. Springer. 2021. P. 392–399. DOI: 10. 1007/978-981-19-0390-8_103.

Bezmaternykh P.V., Vylegzhanin D.V., Gladilin S.A., Nikolaev D.P. 2D barcodes generative recognition. Artificial Intelligence and Decision Making. 2010. No. 4. P. 63–69.

Xiao Q., Liu M., Liu Y. A new binarization method for PDF417 bar code by camera phone. IEEE International Conference on Automation and Logistics (ICAL), Qingdao, China, September 1–3, 2008. IEEE. 2008. P. 1904–1908. DOI: 10.1109/ICAL.2008.4636470.

Chen R., Yu Y., Xu X., et al. Adaptive binarization of QR code images for fast automatic sorting in warehouse systems. Sensors. 2019. Vol. 19, no. 24. P. 5466. DOI: 10.3390/s19245466.

Yang X., Gao X., Jia S.Q., Lu Q.Y. A Method for Extracting QR Code from Complex Background Based on Morphology. Applied Mechanics and Materials. 2013. Vol. 239. P. 1466–1471. DOI: 10.4028/www.scientific.net/AMM.239-240.1466.

Li D., Zhang L., Jin X. An improvement for PDF417 code authentication on mobile phone terminals based on code feature analysis and watermarking. Multimedia Systems. 2022. Vol. 28, no. 5. P. 1585–1596. DOI: 10.1109/ICIEA.2011.5975630.

Li J.-H., Wang W.-H., Rao T.-T., et al. Morphological segmentation of 2-D barcode gray scale image. International Conference on Information System and Artificial Intelligence (ISAI), Hong Kong, China, June 24–26 2016. IEEE. 2016. P. 62–68. DOI: 10.1109/ISAI.2016.0022.

Trummer M., Denzler J. Reading out 2D Barcode PDF417. 2007. DOI: 10.1007/978-1-84628-945-3_19.

Zamberletti A., Gallo I., Albertini S., Noce L. Neural 1D barcode detection using the Hough transform. IPSJ Transactions on Computer Vision and Applications. 2015. Vol. 7. P. 1–9. DOI: 10.2197/ipsjtcva.7.1.

Szentandr´asi I., Herout A., Dubsk´a M. Fast detection and recognition of QR codes in high-resolution images. Proceedings of the 28th spring conference on computer graphics, Budmerice, Slovakia, May 2–4, 2012. 2012. P. 129–136. DOI: 10.1145/2448531.2448548.

Hu D., Chen X., Yu D., Li D. Algorithm for detecting the rows boundary of the PDF417 barcode. / ed. by L. Zhang, J. Zhang, M. Liao. Oct. 2005. 60431Z. DOI: 10.1117/12.654952.

Aliev M., Kunina I., Nikolaev D., Polevoy D. On the practical aspects of computing the Hough image by the Brady-Yong algorithm. Informatsionnye protsessy. 2023. Vol. 23, no. 2. P. 250–273. DOI: 10.53921/18195822_2023_23_2_250.

Fischler M.A., Bolles R.C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM. 1981. June. Vol. 24, no. 6. P. 381–395. DOI: 10.1145/358669.358692.




DOI: http://dx.doi.org/10.14529/cmse240402