International E-publication: Publish Projects, Dissertation, Theses, Books, Souvenir, Conference Proceeding with ISBN. 

Deep Attention Models for Identification of Laser Printed Document Origins

Author Affiliations

  • 1Department of Computer Science, Govt. First Grade College Mahagaon Cross, Kalaburagi, Karnataka, India

Res. J. Recent Sci., Volume 15, Issue (3), Pages 81-85, July,2 (2026)

Abstract

In the field of digital forensic science, artificial intelligence (AI) technologies are being used more and more to settle document-related disputes that have historically required the knowledge of human experts. Finding the precise printer that generated a given document is one of the main goals of intelligent systems based on printer identification. Nevertheless, a lot of current methods rely on text-dependent approaches, which might not work in some forensic situations. These drawbacks have spurred research into text-independent methods using word images from various laser printer models. In this work, laser printer models are classified using grayscale word images. The constructed dataset consists of 100,000-word images collected from five distinct laser printer models. A deep learning–based Convolutional Neural Network (CNN) is employed to identify the source laser printer model. The performance of the proposed CNN architecture is evaluated and compared with recent studies reported in the literature, particularly those based on textural feature analysis. Experimental results demonstrate that the proposed CNN model achieves a high classification accuracy of 98.8%, outperforming several existing methods.

References

  1. Gebhardt, J., Goldstein, M., Shafait, F., & Dengel, A. (2013)., Document authentication using printing technique features and unsupervised anomaly detection., In 2013 12th International conference on document analysis and recognition (pp. 479-483). IEEE.
  2. Khanna, N., Mikkilineni, A. K., Chiu, G. T. C., Allebach, J. P., & Delp, E. J. (2008)., Survey of scanner and printer forensics at purdue university. In International Workshop on Computational Forensics (pp. 22-34)., Berlin, Heidelberg: Springer Berlin Heidelberg.
  3. Ferreira, A., Navarro, L. C., Pinheiro, G., dos Santos, J. A., & Rocha, A. (2015)., Laser printer attribution: Exploring new features and beyond., Forensic science international, 247, 105-125.
  4. Elkasrawi, S., & Shafait, F. (2014)., Printer identification using supervised learning for document forgery detection., In 2014 11th IAPR International Workshop on Document Analysis Systems (pp. 146-150). IEEE.
  5. Shang, S., Memon, N., & Kong, X. (2014)., Detecting documents forged by printing and copying., EURASIP Journal on Advances in Signal Processing, 2014(1), 140.
  6. Schreyer, M., Schulze, C., Stahl, A., & Effelsberg, W. (2009)., Intelligent Printing Technique Recognition and Photocopy Detection for Forensic Document Examination., In Informatiktage (Vol. 8, pp. 39-42).
  7. Lampert, C. H., Mei, L., & Breuel, T. M. (2006)., Printing technique classification for document counterfeit detection., In 2006 International Conference on Computational Intelligence and Security (Vol. 1, pp. 639-644). IEEE.
  8. Wu, Y., Kong, X., You, X. G., & Guo, Y. (2009)., Printer forensics based on page document, In 2009 16th IEEE International Conference on Image Processing (ICIP) (pp. 2909-2912). IEEE.
  9. Devi, M. U., Rao, C. R., & Jayaram, M. (2014)., Statistical measures for differentiation of photocopy from print technology forensic perspective., International Journal of Computer Applications, 105(15).
  10. Gonasagi, P., Rumma, S. S., & Hangarge, M. (2023)., Text-independent source identification of printed documents using texture features and CNN model., In First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022) (pp. 250-261). Atlantis Press.
  11. Ferreira, A., Bondi, L., Baroffio, L., Bestagini, P., Huang, J., Dos Santos, J. A., ... & Rocha, A. (2017)., Data-driven feature characterization techniques for laser printer attribution., IEEE Transactions on Information Forensics and Security, 12(8), 1860-1873.
  12. Jain, H., Joshi, S., Gupta, G., & Khanna, N. (2020)., Passive classification of source printer using text-line-level geometric distortion signatures from scanned images of printed documents., Multimedia Tools and Applications, 79(11), 7377-7400.
  13. Joshi, S., Saxena, S., & Khanna, N. (2020)., Source printer identification from document images acquired using smartphone., arXiv preprint arXiv:2003.12602.
  14. Bibi, M., Hamid, A., Moetesum, M., & Siddiqi, I. (2019)., Document forgery detection using printer source identification—a text-independent approach., In 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW) (Vol. 8, pp. 7-12). IEEE.
  15. Darwish, S. M., & ELgohary, H. M. (2021)., Building an expert system for printer forensics: A new printer identification model based on niching genetic algorithm., Expert Systems, 38(2), e12624.
  16. Otsu, N. (1979)., A threshold selection method from gray-level histograms., Automatica, 11(285-296).
  17. Hangarge, M., Santosh, K. C., Doddamani, S., & Pardeshi, R. (2013)., Statistical texture features based handwritten and printed text classification in south Indian documents., arXiv preprint arXiv:1303.3087.
  18. Gonasagi, P., Rumma, S. S., & Hangarge, M. (2020)., Classification of historical documents based on LBP and LPQ techniques., Int J Innov Technol Exploring Eng , 9(3).
  19. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012)., Imagenet classification with deep convolutional neural networks., Advances in neural information processing systems, 25.
  20. Ioffe, S., & Szegedy, C. (2015)., Batch normalization: Accelerating deep network training by reducing internal covariate shift., In International conference on machine learning (pp. 448-456). pmlr.
  21. Fix, E. (1985)., Discriminatory analysis: nonparametric discrimination, consistency properties (Vol. 1)., USAF school of Aviation Medicine.
  22. Gonasagi, P., Rumma, S. S., & Hangarge, M. (2023, August)., Text-independent source identification of printed documents using texture features and CNN model., In First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022) (pp. 250-261). Atlantis Press.