U-NET ARCHITECTURE NEURAL NETWORK FOR LOCALIZATION OF DIGITAL IMAGES INTEGRITY VIOLATION
Subject of Research. The paper presents the study of the U-Net architecture neural network applicability to localization problem of image modifications. The implemented method provides the detecting of the modified image and getting a mask of the changed area. Method. The proposed method was based o...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Saint Petersburg National Research University of Information Technologies, Mechanics and Optics (ITMO University)
2020-07-01
|
| Series: | Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki |
| Subjects: | |
| Online Access: | https://ntv.ifmo.ru/file/article/19642.pdf |
| _version_ | 1818528325108236288 |
|---|---|
| author | Kristina M. Abdullina Anton I. Spivak |
| author_facet | Kristina M. Abdullina Anton I. Spivak |
| author_sort | Kristina M. Abdullina |
| collection | DOAJ |
| description | Subject of Research. The paper presents the study of the U-Net architecture neural network applicability to localization problem of image modifications. The implemented method provides the detecting of the modified image and getting a mask of the changed area. Method. The proposed method was based on deep machine learning – a neural network. U-Net neural network architecture was studied. The training dataset was created as a basis for model training with
original images and images modified using a graphical editor. The implemented method represents image as a set of pixels. Main Results. The trained model has shown a high level of brightness recognition for image modifications, up to 80 %, and up to 64 % for copy-shift. Practical Relevance. The result can be practically applicable in the forensics for recognition of modified image blocks and for copyright protection. |
| first_indexed | 2024-12-11T06:48:19Z |
| format | Article |
| id | doaj.art-ac483343618b4a4bb488ad9216e73f53 |
| institution | Directory Open Access Journal |
| issn | 2226-1494 2500-0373 |
| language | English |
| last_indexed | 2024-12-11T06:48:19Z |
| publishDate | 2020-07-01 |
| publisher | Saint Petersburg National Research University of Information Technologies, Mechanics and Optics (ITMO University) |
| record_format | Article |
| series | Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki |
| spelling | doaj.art-ac483343618b4a4bb488ad9216e73f532022-12-22T01:17:01ZengSaint Petersburg National Research University of Information Technologies, Mechanics and Optics (ITMO University)Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki2226-14942500-03732020-07-0120342543110.17586/2226-1494-2020-20-3-425-431U-NET ARCHITECTURE NEURAL NETWORK FOR LOCALIZATION OF DIGITAL IMAGES INTEGRITY VIOLATIONKristina M. Abdullina0https://orcid.org/0000-0003-1952-8561Anton I. Spivak1https://orcid.org/0000-0002-6981-8754Student, ITMO University, Saint Petersburg, 197101, Russian FederationPhD, Associate Professor, ITMO University, Saint Petersburg, 197101, Russian Federation; Researcher, St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS), Saint Petersburg, 199178, Russian FederationSubject of Research. The paper presents the study of the U-Net architecture neural network applicability to localization problem of image modifications. The implemented method provides the detecting of the modified image and getting a mask of the changed area. Method. The proposed method was based on deep machine learning – a neural network. U-Net neural network architecture was studied. The training dataset was created as a basis for model training with original images and images modified using a graphical editor. The implemented method represents image as a set of pixels. Main Results. The trained model has shown a high level of brightness recognition for image modifications, up to 80 %, and up to 64 % for copy-shift. Practical Relevance. The result can be practically applicable in the forensics for recognition of modified image blocks and for copyright protection.https://ntv.ifmo.ru/file/article/19642.pdfimagesmodificationneural networksu-netinformation security |
| spellingShingle | Kristina M. Abdullina Anton I. Spivak U-NET ARCHITECTURE NEURAL NETWORK FOR LOCALIZATION OF DIGITAL IMAGES INTEGRITY VIOLATION Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki images modification neural networks u-net information security |
| title | U-NET ARCHITECTURE NEURAL NETWORK FOR LOCALIZATION OF DIGITAL IMAGES INTEGRITY VIOLATION |
| title_full | U-NET ARCHITECTURE NEURAL NETWORK FOR LOCALIZATION OF DIGITAL IMAGES INTEGRITY VIOLATION |
| title_fullStr | U-NET ARCHITECTURE NEURAL NETWORK FOR LOCALIZATION OF DIGITAL IMAGES INTEGRITY VIOLATION |
| title_full_unstemmed | U-NET ARCHITECTURE NEURAL NETWORK FOR LOCALIZATION OF DIGITAL IMAGES INTEGRITY VIOLATION |
| title_short | U-NET ARCHITECTURE NEURAL NETWORK FOR LOCALIZATION OF DIGITAL IMAGES INTEGRITY VIOLATION |
| title_sort | u net architecture neural network for localization of digital images integrity violation |
| topic | images modification neural networks u-net information security |
| url | https://ntv.ifmo.ru/file/article/19642.pdf |
| work_keys_str_mv | AT kristinamabdullina unetarchitectureneuralnetworkforlocalizationofdigitalimagesintegrityviolation AT antonispivak unetarchitectureneuralnetworkforlocalizationofdigitalimagesintegrityviolation |