Advertisement

Multimedia Tools and Applications

, Volume 78, Issue 1, pp 897–912 | Cite as

Quick response barcode deblurring via doubly convolutional neural network

  • Haitao Pu
  • Mingqu Fan
  • Jinliang Yang
  • Jian LianEmail author
Article

Abstract

Various image preprocessing applications for two dimensional (2D) barcode involve reversing the degradation operations (e.g. deblurring). Most of the previously proposed deblurring approaches focus on the construction of suitable deconvolution models, which have shown significant performance at laboratory level. However, the model-based image deblurring solutions might not work well in practical scenarios. To deal with this problem, we propose a convolutional neural network (CNN) based framework to tackle the parameter-free situation for 2D barcode deblurring. The proposed solution leverages the deep learning technique to bridge the gap between traditional model-based methods and requirement of reversing the blurry 2D barcode images. Experiments on practically blurred quick response (QR) barcode images demonstrate that the proposed approach achieves the superior performance in comparison with state-of-the-art model-based image deblurring approaches.

Keywords

Image Processing Deblurring Convolutional Neural Network 2D barcode 

Notes

Acknowledgements

The authors would like to thank the reviewers and editors. This work was financially supported by the Teaching Reform Research Project of Shandong University of Finance and Economics (2891470), Teaching Reform Research Project of Undergraduate Colleges and Universities of Shandong Province (2015 M136), SDUST Excellent Teaching Team Construction Plan (JXTD20160512) and Jinan campus of SDUST Excellent Teaching Team Construction Plan (JNJXTD201711), SDUST Young Teachers Teaching Talent Training Plan (BJRC20160509), Teaching research project of Shandong University of Science and Technology (JG201509 and qx2013286), Shandong Province Science and Technology Major Project (2015ZDXX0801A02) and National Natural Science Foundation of China (61703243). We would like to appreciate the reviewers and editors for their valuable comments.

Authors Disclosures

The authors declare no conflict of interest. The funding sponsors had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, and in the decision to publish the results.

References

  1. 1.
    Battiato S (2002) Restoration of out-of-focus images based on circle of confusion estimate. Proceedings of SPIE - The International Society for Optical Engineering 4790(2):408–416Google Scholar
  2. 2.
    Bengio Y, Lamblin P, Popovici D, Larochelle H et al (2007) Greedy layer-wise training of deep networks. Adv Neural Inf Proces Syst 19:153Google Scholar
  3. 3.
    Boulanger-Lewandowski N, Bengio Y, Vincent P (2012) Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription, arXiv preprint arXiv:1206.6392Google Scholar
  4. 4.
    Chan TF, Wong CK (1998) Total variation blind deconvolution. IEEE Transactions on Image Processing. A Publication of the IEEE Signal Processing Society 7(3):370–375Google Scholar
  5. 5.
    Choksi R, van Gennip Y, Oberman A (2017) Anisotropic total variation regularized l^1-approximation and denoising/deblurring of 2d bar codes. Inverse Prob Imaging 5(3):591–617MathSciNetCrossRefGoogle Scholar
  6. 6.
    Chu CH, Yang DN, Pan YL, Chen MS (2011) Stabilization and extraction of 2d barcodes for camera phones. Multimedia Systems 17(2):113–133CrossRefGoogle Scholar
  7. 7.
    Collobert R, Weston J, Bottou L, Karlen M, Kavukcuoglu K, Kuksa P (2011) Natural language processing (almost) from scratch. The Journal of Machine Learning Research 12:2493–2537zbMATHGoogle Scholar
  8. 8.
    Dahl G, Mohamed A-r, Hinton GE, et al (2010) Phone recognition with the mean-covariance restricted Boltzmann machine, in: Advances in neural information processing systems, pp. 469–477Google Scholar
  9. 9.
    Dahl GE, Yu D, Deng L, Acero A (2012) Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. Audio, Speech, and Language Processing, IEEE Transactions on 20(1):30–42CrossRefGoogle Scholar
  10. 10.
    Dan TU, Gan YL, Zong-Qi XU (2007) A real-time deblurring algorithm for the qr barcode images. Computer Engineering & Science 29(3):43–45Google Scholar
  11. 11.
    Deng L, Seltzer ML, Yu D, Acero A, Mohamed A-R, Hinton GE (2010) Binary coding of speech spectrograms using a deep auto-encoder., in: Interspeech, Citeseer, pp. 1692–1695Google Scholar
  12. 12.
    Gennip YV, Athavale P, Gilles J, Choksi R (2015) A regularization approach to blind deblurring and denoising of qr barcodes. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society 24(9):2864–2873MathSciNetCrossRefGoogle Scholar
  13. 13.
    Gregersen E, Code QR (2014) https://www.britannica.com/ technology/QR-Code, [Online; accessed 02-July-2014]
  14. 14.
    Guo D, Liu R, Wang X, Lan F (2013) QR barcode decoding chip and decoding method thereof. US Patent 8,550,352, 8 October 2013Google Scholar
  15. 15.
    Hinton GE, Osindero S, Teh Y-W (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554MathSciNetCrossRefGoogle Scholar
  16. 16.
    Hsu HH, Chang MH, Yen NY (2012) A health management application with qr code input and rule inference, in: International Conference on Information Security and Intelligence Control, pp. 119–122Google Scholar
  17. 17.
    Jain V, Seung S (2009) Natural image denoising with convolutional networks, in: Ad-vances in Neural Information Processing Systems, pp. 769–776Google Scholar
  18. 18.
    Jalobeanu A, Blancferaud L, Zerubia J (2004) An adaptive gaussian model for satellite image deblurring. IEEE Trans Image Process 13(4):613–621CrossRefGoogle Scholar
  19. 19.
    Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: Convolutional architecture for fast feature embedding, in: Proceedings of the ACM International Conference on Multimedia, ACM,pp. 675–678Google Scholar
  20. 20.
    Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks, in: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 1725–1732Google Scholar
  21. 21.
    Kim YG, Woo E (2016) Consumer acceptance of a quick response (qr) code for the food traceability system: Application of an extended technology acceptance model (tam). Food Res Int 85:266–272CrossRefGoogle Scholar
  22. 22.
    Krishnan D, Fergus R (2009) Fast image deconvolution using hyper-laplacian priors. in nips, in: Advances in Neural Information Processing Systems 22: Conference on Neural Information Processing Systems 2009. Proceedings of A Meeting Held 7–10 December 2009, Vancouver, British Columbia, pp. 1033–1041Google Scholar
  23. 23.
    Krishnan D, Tay T, Fergus R (2011) Blind deconvolution using a normalized sparsity measure, in: Computer Vision and Pattern Recognition, pp. 233–240Google Scholar
  24. 24.
    Krishnan D, Bruna J, Fergus R. (2013) Blind Deconvolution with Non-local Sparsity Reweighting. arXiv:1311.4029Google Scholar
  25. 25.
    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks, in: Advances in neural information processing systems, pp. 1097–1105Google Scholar
  26. 26.
    Kundur D, Hatzinakos D (2002) Blind image deconvolution. IEEE Signal Process Mag 13(3):43–64CrossRefGoogle Scholar
  27. 27.
    LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324CrossRefGoogle Scholar
  28. 28.
    Levin A (2006) Blind motion deblurring using image statistics 841–848Google Scholar
  29. 29.
    Levin A, Weiss Y, Durand F, Freeman WT (2009) Understanding and evaluating blind deconvolution algorithms, in: Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pp. 1964–1971Google Scholar
  30. 30.
    Lin P (2016) Distributed secret sharing approach with cheater prevention based on qrcode. IEEE Transactions on Industrial Informatics 12(1):384–392Google Scholar
  31. 31.
    Liu Y, Yang J, Liu M (2008) Recognition of qr code with mobile phones, in: Control and Decision Conference, 2008, pp. 203–206CcdcGoogle Scholar
  32. 32.
    Liu N, Zheng X, Sun H, Tan X (2013) Two-dimensional bar code out-of-focus deblurring via the increment constrained least squares filter. Pattern Recogn Lett 34(2):124–130CrossRefGoogle Scholar
  33. 33.
    Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440Google Scholar
  34. 34.
    Man M S, Dwivedi A, Sonkar C, Prasad R (2012) A QR Code Based Processing For Dynamic and Transparent Seat Allocation in Indian Railway. International Journal of Computer Science Issues. http://www.ijcsi.org/papers/IJCSI-9-3-1-338-344.pdf
  35. 35.
    Ouaviani P, Bottazzi B, Caselli G (2002) A common image processing framework for 2d barcode reading 2: 652–655Google Scholar
  36. 36.
    Pnevmatikakis EA, Soudry D, Gao Y, Machado TA, Merel J, Pfau D, Reardon T, Mu Y, Lacefield C, Yang W (2016) Simultaneous denoising, deconvolution, and demixing of calcium imaging data. Neuron 89(2):285CrossRefGoogle Scholar
  37. 37.
    Prasoon A, Petersen K, Igel C, Lauze F, Dam E, Nielsen M (2013) Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network, in: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2013, Springer, pp. 246–253Google Scholar
  38. 38.
  39. 39.
    Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556Google Scholar
  40. 40.
    Simonyan K, Vedaldi A, Zisserman A (2013) Deep inside convolutional networks: Visualising image classification models and saliency maps, arXiv preprint arXiv:1312.6034Google Scholar
  41. 41.
    Sixou B, Toma A, Denis L, Peyrin F (2017) Iterative choice of the optimal regularization parameter in tv image deconvolution. Inverse Problems & Imaging 9(4):1171–1191zbMATHGoogle Scholar
  42. 42.
    Socher R, Huval B, Bath B, Manning CD, Ng AY (2012) Convolutional-recursive deep learning for 3d object classification, in: Advances in Neural Information Processing Systems, pp. 665–673Google Scholar
  43. 43.
    Sörös G, Semmler S, Humair L, Hilliges O (2015) Fast blur removal for wearable qr code scanners. ACM International Symposium on Wearable Computers. ACM, New York, pp 117–124Google Scholar
  44. 44.
    Stork DG, Gill PR (2014) Reading qr code symbols with an ultra-miniature com-putational diffractive imager, in: Computational Optical Sensing and ImagingGoogle Scholar
  45. 45.
    Tai YW, Tan P, Brown MS (2011) Richardson-lucy deblurring for scenes under a projective motion path. IEEE Transactions on Pattern Analysis & Machine Intelligence 33(8):1603–1618CrossRefGoogle Scholar
  46. 46.
    Tarjan L, Enk I, Tegeltija S, Stankovski S, Ostojic G (2014) A readability analysis for qr code application in a traceability system. Computers & Electronics in Agriculture 109(109):1–11CrossRefGoogle Scholar
  47. 47.
    Turaga SC, Murray JF, Jain V, Roth F, Helmstaedter M, Briggman K, Denk W, Seung HS (2010) Convolutional networks can learn to generate affinity graphs for image segmentation. Neural Comput 22(2):511–538CrossRefGoogle Scholar
  48. 48.
    Walsh A (2010) Qr codes: Using mobile phones to deliver library instruction and help at the point of need. Journal of Information Literacy 4(1):55–65CrossRefGoogle Scholar
  49. 49.
    Weston J, Bengio S, Usunier N (2010) Large scale image annotation: learning to rank with joint word-image embeddings. Mach Learn 81(1):21–35MathSciNetCrossRefGoogle Scholar
  50. 50.
    Zbar bar code reader, https://zbar.sourceforge.netGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Haitao Pu
    • 1
  • Mingqu Fan
    • 1
  • Jinliang Yang
    • 1
  • Jian Lian
    • 1
    Email author
  1. 1.Department of Electronic Engineering Information TechnologyShandong University of Sci&TechJinanChina

Personalised recommendations