Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Electronic and Information Engineering | en_US |
| dc.contributor.advisor | Law, N. F. Bonnie (EIE) | - |
| dc.creator | Jiang, Hao | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/9570 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | PRNU-based multi-scale analysis for tampering detection | en_US |
| dcterms.abstract | An accurate tampering detection is still an open problem in the field of image forensics and locating the subtle tampering area is demanding more research work. In this thesis, we introduce some strategies to solve this problem and investigate the influence of image content on the tampering detection process. Firstly, inspired by the recent research on the multi-scale forgeries detecting strategies, a combination of different tampering probability maps from one image is utilized to build-up a single map so as to strengthen the results with threshold drift and content-dependent neighborhood interaction. Then two new approaches called adaptive window and segmentation guided are studied. The adaptive window method changes the size of detecting window while content inside the detecting window is changing. The segmentation guided method utilizes the central segment correlation in each analysis window to calculate decision statistic more precisely. Extensive experiments have been carried out to study the influence of image content on the result from different tampering strategies. In particular, experiments investigating the effect of image contents including intensity level, size of forgery area and texture complexity have been done. Results show that both the adaptive window and segmentation guided provide better results than state-of-the-art tampering detection methods. The adaptive window method has a lower computational complexity than the segmentation guided approach. | en_US |
| dcterms.extent | 75 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2018 | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.LCSH | Digital images -- Editing | en_US |
| dcterms.LCSH | Image analysis | en_US |
| dcterms.LCSH | Image processing -- Digital techniques | en_US |
| dcterms.LCSH | Forensic sciences -- Data processing | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 991022144625003411.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 1.81 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/9570