Skip to main content
SpringerLink
Log in

Zernike-CNNs for image preprocessing and classification in printed register detection

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In the register detection of printing field, a new approach based on Zernike-CNNs is proposed. The edge feature of image is extracted by Zernike moments (ZMs), and a recursive algorithm of ZMs called Kintner method is derived. An improved convolutional neural networks (CNNs) are investigated to improve the accuracy of classification. Based on the classic convolutional neural network (CNN), the improved CNNs adopt parallel CNN to enhance local features, and adopt auxiliary classification part to modify classification layer weights. A printed image is trained with 7 × 400 samples and tested with 7 × 100 samples, and then the method in this paper is compared with other methods. In image processing, Zernike is compared with Sobel method, Laplacian of Gaussian (LoG) method, Smallest Univalue Segment Assimilating Nucleus (SUSAN) method, Finite Impusle Response (FIR) method, Multi-scale Morphological Gradient (MMG) method. In image classification, improved CNNs are compared with classical CNN. The experimental results show that Zernike-CNNs have the best performance, the mean square error (MSE) of the training samples reaches 0.0143, and the detection accuracy of training samples and test samples reached 91.43% and 94.85% respectively. The experiments reveal that Zernike-CNNs are a feasible approach for register detection.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  1. Abdel-Hamid O, Mohamed AR, Jiang H, Deng L, Penn G, Yu D (2014) Convolutional neural networks for speech recognition. IEEE/ACM Transactions on Audio Speech & Language Processing 22(10):1533–1545

    Article  Google Scholar 

  2. Aggarwal A, Singh C (2016) Zernike moments-based gurumukhi character recognition. Appl Artif Intell 30(4–6):429–444

    Article  Google Scholar 

  3. Anand S, Kaur S (2015) Empirical analysis of rotation invariance in moment coefficients. Int J Comput Appl 119(15):19–26

    Google Scholar 

  4. Chen Z, Cai H, Zhang Y, Wu C, Sotelo MA (2019) A novel sparse representation model for pedestrian abnormal trajectory understanding. Expert Syst Appl 138:112753

    Article  Google Scholar 

  5. Chen YF, Hsieh YH, Yu YT, Lai YH, Hsieh MX (2019) The integral-based parallel algorithm for the fast generation of the zernike polynomials. Opt Express 28(2)

  6. Chong CW, Raveendran P, Mukundan R (2003) An efficient algorithm for fast computation of pseudo-zernike moments. Int J Pattern Recognit Artif Intell 17(06):1011–1023

    Article  Google Scholar 

  7. Chu J, Guo Z, Leng L (2018) Object detection based on multi-layer convolution feature fusion and online hard example mining. IEEE access, 19959-19967

  8. Diop EHS, Angulo J (2020) Inhomogeneous morphological pdes for robust and adaptive image shock filters. IET Image Process 14(6):1035–1046

    Article  Google Scholar 

  9. Dixit R, Naskar R, Mishra S (2017) Blur-invariant copy-move forgery detection technique with improved detection accuracy utilising swt-svd. IET Image Process 11(5):301–309

    Article  Google Scholar 

  10. Fairchild MD (2013). Color appearance models. JOHN WILEY & SONS, INC

  11. Fernando M, Wijayanayake J (2015) Novel approach to use hu moments with image processing techniques for real time sign language communication

  12. Firuzi K, Vakilian M, Phung BT, Blackburn TR (2019) Partial discharges pattern recognition of transformer defect model by lbp & hog features. IEEE Transactions on Power Delivery 34(2):542–550

    Article  Google Scholar 

  13. Ji-Wen C, Jiu-Bin T (2005) Algorithm for edge subpixel location based on zernike moment. Optical technique 31(5):779–782+785

    Google Scholar 

  14. Jongsu L, Soosung P, Kee-Hyun S, et al (2018) Smearing defects: a root cause of register measurement error in roll-to-roll additive manufacturing system. Int J Adv Manuf Technol. 3155–3165

  15. Kang HR (2006) Computational color technology (SPIE press monograph Vol. PM159). SPIE- International Society for Optical Engineering.

  16. Kang HK, Lee CW, Lee JM, Shin KH (2010) Cross direction register modeling and control in a multi-layer gravure printing. J Mech Sci Technol 24(1):391–397

    Article  Google Scholar 

  17. Kang H, Lee C, Shin K (2013) Modeling and compensation of the machine directional register in roll-to-roll printing. Control Eng Pract 21(5):645–654

    Article  Google Scholar 

  18. Kaur H, Pannu HS (2019) Zernike moments-based fingerprint recognition using weighted-support vector machine. Modern Physics Letters B 33:1950245

    Article  MathSciNet  Google Scholar 

  19. Kim CH, You HI, Lee SH (2012) Register control of roll-to-roll gravure-offset printing equipment considering time difference between measurement and actuation. Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering ence 226(11):2726–2738

    Article  Google Scholar 

  20. Krizhevsky A, Sutskever I, Hinton, Geoffrey E (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84–90

    Article  Google Scholar 

  21. Kumar MB, Pushpalakshmi R (2018). Multiple kernel scale invariant feature transform and cross indexing for image search and retrieval. The imaging science journal.

  22. Lee J, Shin K, Lee C (2015) Analysis of dynamic thermal characteristic of register of roll-to-roll multi-layer printing systems. Robot Comput Integr Manuf 35(oct.):77–83

    Article  Google Scholar 

  23. Lee J, Seong J, Park J, Park S, Lee D, Shin KH (2015) Register control algorithm for high resolution multilayer printing in the roll-to-roll process. Mech Syst Signal Process, 60-61(aug.), 706-714

  24. Lee J, Isto P, Jeong H, Park J, Lee D, Shin KH (2016) Register mark measurement errors in high-precision roll-to-roll continuous systems: the effect of register mark geometry on measurement error. Appl Phys Lett 109(14):2925

    Article  Google Scholar 

  25. Leng L, Yang Z, Kim C, Zhang Y (2020) A light-weight practical framework for feces detection and trait recognition. Sensors 20(9):2644

    Article  Google Scholar 

  26. Li Y, Huo J, Yang M, Zhang G (2018) Algorithm of locating the sphere center imaging point based on novel edge model and zernike moments for vision measurement. J Mod Opt, 1-10

  27. Luo J, Zhang Z (2003) Automatic colour printing inspection by image processing. Journal of Materials Processing Tech 139(1–3):373–378

    Article  Google Scholar 

  28. Lupek M, Matějka P, Volka K (2010) Noise reduction in raman spectra: finite impulse response filtration versus savitzky–golay smoothing. J Raman Spectrosc 38(9)

  29. Mukundan CWCR (2003) A comparative analysis of algorithms for fast computation of zernike moments. Pattern Recogn 36(3):731–742

    Article  Google Scholar 

  30. Müller O, Rejkuba M, Jerjen H (2018) Tip of the red giant branch distances to the dwarf galaxies dw1335-29 and dw1340-30 in the centaurus group. Astron Astrophys 615:A96

    Article  Google Scholar 

  31. Nazarkevych M, Izonin I, Ml MG, Lotoshynska N (2020) An approach towards the protection for printed documents by means of latent elements with fractal grids and electronic determination of its authenticity

  32. Robin T, Schirrmeiste J, Tobias, Springenberg et al (2017) Deep learning with convolutional neural networks for EEG decoding and visualization. Hum Brain Mapp 38:5391–5420

    Article  Google Scholar 

  33. Sugimoto T (2010). Development of new type gravure register controller. Journal of Printing ence & Technology, 24.

  34. Verma OP, Parihar AS (2017) An optimal fuzzy system for edge detection in color images using bacterial foraging algorithm. IEEE Trans Fuzzy Syst 20(1):114–127

    Article  Google Scholar 

  35. Vidi I, Egnell L, Jerome NP, Teruel JR, Sjbakk TE, Stlie A et al (2018) Support vector machine for breast cancer classification using diffusion-weighted mri histogram features: preliminary study. J Magn Reson Imaging 47:1205–1216

    Article  Google Scholar 

  36. Wee CY, Paramesran R, Takeda F (2004) New computational methods for full and subset zernike moments. Inf Sci 159(3–4):203–220

    Article  MathSciNet  Google Scholar 

  37. Xue-lin W, Yan-qiu C (2011) Detection algorithm of color printing registration deviation based on edge co-occurrence conditional probability matrix. Comput Eng 37(13):285–287+290

    Google Scholar 

  38. Yasaka K, Akai H, Mackin D, Court L, Kiryu S (2017) Precision of quantitative computed tomography texture analysis using image filtering. Medicine 96(21):e6993

    Article  Google Scholar 

  39. Yoshida T, Takagi S, Shen T, Muto Y (2008) Modeling and cooperative resister control of gravure printing press. Transactions of the Japan Society of Mechanical Engineers 74(738):339–345

    Article  Google Scholar 

  40. Yoshida T, Takagi S, Muto Y, Shen T (2008) Modeling and resister control of sectional drive gravure printing press. Transactions of the Japan Society of Mechanical Engineers 74(742):1438–1444

    Article  Google Scholar 

Download references

Acknowledgements

The authors would acknowledge the anonymous reviewers and editors for their invaluable comments. The work was supported in part by the industrial science and technology project of Shaanxi province of China under Grant 2016GY-141, in part by the science plan program of Xi’an City under Grant 201787CG/RC050 (XJCY001), in part by the Research Fund of Xijing University of China under Grant XJ160232.

Author information

Authors and Affiliations

  1. Xijing University, Xi’an, 710123, Shaanxi, China

    Wang Sheng, Lv Lin-Tao & Yang Hong-Cai

  2. Xi’an University of Architecture and Technology, Xi’an, 710055, Shaanxi, China

    Lu Di

Authors
  1. Wang Sheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lv Lin-Tao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yang Hong-Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Lu Di
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wang Sheng.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, S., Lv, LT., Yang, HC. et al. Zernike-CNNs for image preprocessing and classification in printed register detection. Multimed Tools Appl 80, 32409–32421 (2021). https://doi.org/10.1007/s11042-021-10981-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-021-10981-2

Keywords

Search

Navigation