25, May 2026

Automated Printed Document Dating Using Deep Learning

VOLUME-12; ISSUE-5; MAY-2026

Author(s): Dr. Pushpalata Gonasagi

Authors Affiliations:

Associate Professor, Department of Computer Science,

Govt. First Grade College, Mahagaon Cross, Kalaburagi, India

DOIs:10.2015/IJIRMF/202605016     |     Paper ID: IJIRMF202605016


Abstract
Keywords
Cite this Article/Paper as
References

Document age identification plays an important role in forensic document examination for detecting forged or manipulated documents. Traditional approaches rely on handcrafted feature extraction techniques such as Histogram of Oriented Gradients (HOG), LBP (Local Binay Pattern), Local Phase Quantization (LPQ) and machine learning classifiers like K-Nearest neighbour (KNN), Support Vector Machine (SVM). However, these methods require manual feature engineering and may fail to capture complex degradation patterns in aged documents. This research proposes a Convolutional Neural Network (CNN) with Rectified Linear Unit (ReLU) activation function for automatic document age classification. The model learns texture degradation patterns directly from document images without manual feature extraction. The dataset consists of 200 Life magazine cover pages collected from five diffèrent décades : 1930, 1940, 1950, 1960, and 1970. The proposed CNN model includes convolution layers, ReLU activation layers, max pooling layers, fully connected layers, and SoftMax classification. Experimental results demonstrate that the proposed CNN model achieves an accuracy of 94.8%, outperforming than the traditional methods.

 

CNN, ReLU, Document Age Identification, Deep Learning, Forensic Document Analysis, Image Classification

Dr. Pushpalata Gonasagi (2026); Automated Printed Document Dating Using Deep Learning, International Journal for Innovative Research in Multidisciplinary Field, ISSN(O): 2455-0620, Vol-12, Issue-5, Available on –   https://www.ijirmf.com/

  1. Halder, Biswajit, and Utpal Garain. “Color Feature Based Approach for DeterminingInk Age in Printed Documents.” In Pattern Recognition (ICPR), 2010 20th International Conference on, IEEE, 2010, pp. 3212 3215.
  2. Bertrand, Romain, Petra Gomez-Krämer, Oriol Ramos Terrades, Patrick Franco, and Jean-Marc Ogier. “A System Based on Intrinsic Features for Fraudulent Document Detection.” In Document Analysis and Recognition (ICDAR), 2013 12th International Conference on, pp. 106-110. IEEE, 2013.
  3. Raghunandan, K. S., Palaiahnakote Shivakumara, B. J. Navya, G. Pooja, Navya Prakash, G. Hemantha Kumar, Umapada Pal, and Tong Lu. “Fourier Coefficients for Fraud Handwritten Document Classification through Age Analysis.” In Proc. IEEE International Conference in Frontiers in Handwriting Recognition (ICFHR), 2016, pp. 25-3.1354.
  4. Barboza, Ricardo, Rafael Dueire Lins, and Darlisson Marinho de Jesus. “A Color-Based Model to Determine the Age of Documents for Forensic Purposes.” In Proc. IEEE, Document Analysis and Recognition (ICDAR), 12th International Conference, 2013, pp. 1350-1354
  5. Elkasrawi, Sara, and Faisal Shafait. “Printer identification using supervised learning fo document forgery detection.” In 2014 11th IAPR International Workshop on Document Analysis Systems, pp. 146-150. IEEE, 2014
  6. Pushpalata Gonasagi, Shivanand S Rumma, Mallikarjun Hangarge “Classification of Historical Documents Based on LBP and LPQ Techniques” International Journal of Innovative Technology and Exploring Engineering (IJITEE) ISSN: 2278-3075, Volume-9 Issue-3, January 2020.
  7. Gonasagi, Pushpalata, Shivanand Rumma, and Mallikarjun Hangarge. “Texture Analysis Technique for Document Age Identification.” In Innovations in Computer Science and Engineering: Proceedings of the Ninth ICICSE, 2021, pp. 331-337. Singapore: Springer Singapore, 2022.
  8. Google books at http://books.google.com/
  9. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in neural information processing systems, 25.
  10. Ioffe, S., & Szegedy, C. (2015, June). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning (pp. 448-456). PMLR.
  11. Nair, V., & Hinton, G. E. (2010). Rectified Linear Units Improve Restricted Boltzmann Machines. Proceedings of the 27th International Conference on Machine Learning (ICML), 807–814.
Post Views: 45

Download Full Paper

Download PDF No. of Downloads:12 | No. of Views: 38