Document Forgery Detection
Nandini N1, Keerthi Joshi K2, Devprakash3, Madhura C4, Vandana M Ladwani5
1Nandini N, Department of Computer Science and Engineering, PES University, Bangalore (Karnataka), India.
2Madhura C, Department of Computer Science and Engineering, PES University, Bangalore (Karnataka), India.
3Keerthi Joshi K, Department of Computer Science and Engineering, PES University, Bangalore (Karnataka), India.
4Devprakash B, Department of Computer Science and Engineering, PES University, Bangalore (Karnataka), India.
5Vandana M Ladwani, Department of Computer Science and Engineering, PES University, Bangalore (Karnataka), India.
Manuscript received on 10 May 2023 | Revised Manuscript received on 22 May 2023 | Manuscript Accepted on 15 June 2023 | Manuscript published on 30 June 2023 | PP: 39-42 | Volume-12 Issue-5, June 2023 | Retrieval Number: 100.1/ijeat.E41650612523 | DOI: 10.35940/ijeat.E4165.0612523
Open Access | Editorial and Publishing Policies | Cite | Zenodo | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Document forgery is an increasing problem for both private companies and public administrations. It can be said to represent the loss of time and resources. There are many classical solutions to these problems, such as detecting an integrated security pattern. In such cases, we must resort to forensic techniques for detection. The idea behind using these forensic techniques can also be implemented using artificial intelligence or machine learning, which can be a lower-cost option and provide the same or better results. The experimental results show that multiple models have a strong detection capability for detecting numerous forgeries. In this paper, we present a novel approach to detecting forgeries in documents. The forgery we detect can be classified as hand-written signature forgery and copy-move forgery of any photo, text, or signature. We have developed a novel approach using capsule layers to detect forgery in handwritten signatures. We also use ELA (Error Level Analysis) to detect any errors in the image compression levels.
Keywords: Document, Forgery Detection, Capsule Neural Networks, CNN, Copy-Move Forgery, Signature Forgery
Scope of the Article: Artificial Intelligence