МЕТОД ВИЯВЛЕННЯ ШТУЧНОГО РОЗМИТТЯ ТА ПІДВИЩЕННЯ РІЗКОСТІ ЦИФРОВОГО ЗОБРАЖЕННЯ НА ОСНОВІ АНАЛІЗУ ШУМУ.
Saved in:
| Title: | МЕТОД ВИЯВЛЕННЯ ШТУЧНОГО РОЗМИТТЯ ТА ПІДВИЩЕННЯ РІЗКОСТІ ЦИФРОВОГО ЗОБРАЖЕННЯ НА ОСНОВІ АНАЛІЗУ ШУМУ. |
|---|---|
| Alternate Title: | METHOD FOR DETECTING ARTIFICIAL BLURRING AND SHARPENING OF DIGITAL IMAGES BASED ON NOISE ANALYSIS. |
| Authors: | Дудзинська, Д. С.1 dd.dashikis@gmail.com, Зоріло, В. В.1 vikazorilo@gmail.com |
| Source: | Informatics & Mathematical Methods in Simulation / Informatika ta Matematičnì Metodi v Modelûvannì. 2026, Vol. 16 Issue 3, p488-498. 11p. |
| Subjects: | Digital forensics, Image processing, White noise theory, Internet security |
| Abstract: | The article addresses the актуальну problem of ensuring the integrity of digital images in the context of the rapid development of information technologies, the widespread availability of graphic editors, and artificial intelligence tools. Particular attention is paid to threats associated with the use of forged images in cyberspace, especially in the field of information security and critical infrastructure, including maritime transport. The importance of developing effective methods for detecting image manipulation in order to prevent misinformation and increase trust in digital content is emphasized. The aim of this study is to improve the effectiveness of detecting traces of digital photo editing by developing a method based on the analysis of image noise. The scientific significance of the work lies in advancing approaches to digital image analysis through the use of noise characteristics as an informative indicator of image manipulation. The practical significance consists in the possibility of applying the proposed method in cybersecurity systems and digital forensics for automated forgery detection. The research methodology is based on the use of the Error Level Analysis (ELA) method, statistical analysis of noise characteristics, and computational experimentation. A dataset of 100 digital images was formed, for which typical editing operations, including Gaussian blurring and sharpening, were simulated. Further analysis was performed by constructing and examining noise histograms obtained using ELA. The results of the study reveal characteristic changes in noise histograms caused by blurring and sharpening. In particular, blurring leads to a decrease in noise amplitude and an increase in the central peak, while sharpening results in an expansion of the value range and a decrease in the central peak. Based on these findings, a modification of the ELA method is proposed, enabling automation of the detection process for these types of processing. The proposed method demonstrates high efficiency, with a Type I error rate of 2% and a Type II error rate of 4.5%. The value of the research lies in improving the existing ELA method through the introduction of quantitative criteria for evaluating noise characteristics, which enhances objectivity and expands its application capabilities. The results contribute to the development of digital forensics and information security methods. The practical significance of the work is determined by the possibility of applying the proposed method for automated verification of digital image authenticity in monitoring systems, forensic analysis, journalism, and cybersecurity. [ABSTRACT FROM AUTHOR] |
| Copyright of Informatics & Mathematical Methods in Simulation / Informatika ta Matematičnì Metodi v Modelûvannì is the property of Odessa Polytechnic University and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 194922486 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: МЕТОД ВИЯВЛЕННЯ ШТУЧНОГО РОЗМИТТЯ ТА ПІДВИЩЕННЯ РІЗКОСТІ ЦИФРОВОГО ЗОБРАЖЕННЯ НА ОСНОВІ АНАЛІЗУ ШУМУ. – Name: TitleAlt Label: Alternate Title Group: TiAlt Data: METHOD FOR DETECTING ARTIFICIAL BLURRING AND SHARPENING OF DIGITAL IMAGES BASED ON NOISE ANALYSIS. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Дудзинська%2C+Д%2E+С%2E%22">Дудзинська, Д. С.</searchLink><relatesTo>1</relatesTo><i> dd.dashikis@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Зоріло%2C+В%2E+В%2E%22">Зоріло, В. В.</searchLink><relatesTo>1</relatesTo><i> vikazorilo@gmail.com</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Informatics+%26+Mathematical+Methods+in+Simulation+%2F+Informatika+ta+Matematičnì+Metodi+v+Modelûvannì%22">Informatics & Mathematical Methods in Simulation / Informatika ta Matematičnì Metodi v Modelûvannì</searchLink>. 2026, Vol. 16 Issue 3, p488-498. 11p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Digital+forensics%22">Digital forensics</searchLink><br /><searchLink fieldCode="DE" term="%22Image+processing%22">Image processing</searchLink><br /><searchLink fieldCode="DE" term="%22White+noise+theory%22">White noise theory</searchLink><br /><searchLink fieldCode="DE" term="%22Internet+security%22">Internet security</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: The article addresses the актуальну problem of ensuring the integrity of digital images in the context of the rapid development of information technologies, the widespread availability of graphic editors, and artificial intelligence tools. Particular attention is paid to threats associated with the use of forged images in cyberspace, especially in the field of information security and critical infrastructure, including maritime transport. The importance of developing effective methods for detecting image manipulation in order to prevent misinformation and increase trust in digital content is emphasized. The aim of this study is to improve the effectiveness of detecting traces of digital photo editing by developing a method based on the analysis of image noise. The scientific significance of the work lies in advancing approaches to digital image analysis through the use of noise characteristics as an informative indicator of image manipulation. The practical significance consists in the possibility of applying the proposed method in cybersecurity systems and digital forensics for automated forgery detection. The research methodology is based on the use of the Error Level Analysis (ELA) method, statistical analysis of noise characteristics, and computational experimentation. A dataset of 100 digital images was formed, for which typical editing operations, including Gaussian blurring and sharpening, were simulated. Further analysis was performed by constructing and examining noise histograms obtained using ELA. The results of the study reveal characteristic changes in noise histograms caused by blurring and sharpening. In particular, blurring leads to a decrease in noise amplitude and an increase in the central peak, while sharpening results in an expansion of the value range and a decrease in the central peak. Based on these findings, a modification of the ELA method is proposed, enabling automation of the detection process for these types of processing. The proposed method demonstrates high efficiency, with a Type I error rate of 2% and a Type II error rate of 4.5%. The value of the research lies in improving the existing ELA method through the introduction of quantitative criteria for evaluating noise characteristics, which enhances objectivity and expands its application capabilities. The results contribute to the development of digital forensics and information security methods. The practical significance of the work is determined by the possibility of applying the proposed method for automated verification of digital image authenticity in monitoring systems, forensic analysis, journalism, and cybersecurity. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Informatics & Mathematical Methods in Simulation / Informatika ta Matematičnì Metodi v Modelûvannì is the property of Odessa Polytechnic University and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194922486 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.15276/imms.v16.no3.488 Languages: – Code: ukr Text: Ukrainian PhysicalDescription: Pagination: PageCount: 11 StartPage: 488 Subjects: – SubjectFull: Digital forensics Type: general – SubjectFull: Image processing Type: general – SubjectFull: White noise theory Type: general – SubjectFull: Internet security Type: general Titles: – TitleFull: МЕТОД ВИЯВЛЕННЯ ШТУЧНОГО РОЗМИТТЯ ТА ПІДВИЩЕННЯ РІЗКОСТІ ЦИФРОВОГО ЗОБРАЖЕННЯ НА ОСНОВІ АНАЛІЗУ ШУМУ. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Дудзинська, Д. С. – PersonEntity: Name: NameFull: Зоріло, В. В. IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 07 Text: 2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 22235744 Numbering: – Type: volume Value: 16 – Type: issue Value: 3 Titles: – TitleFull: Informatics & Mathematical Methods in Simulation / Informatika ta Matematičnì Metodi v Modelûvannì Type: main |
| ResultId | 1 |
