| Author: | Gao, Shenglei |
| Title: | Study of crucial factors affecting the accuracy of video source identification for digital forensics |
| Advisors: | Law, N. F. Bonnie (EIE) |
| Degree: | M.Sc. |
| Year: | 2021 |
| Subject: | Image processing -- Digital techniques Digital forensic science Hong Kong Polytechnic University -- Dissertations |
| Department: | Department of Electronic and Information Engineering |
| Pages: | xii, 99 pages : color illustrations |
| Language: | English |
| Abstract: | Photo Response Non-Uniformity (PRNU) based source camera attribution is an effective method to determine whether the image or video is taken from the same photo. This technology works well for various forensics application. It can make judgments through relevant conclusions and even determine the direction of the case. With the large-scale use of digital electronic products and the rapid development of network information, people will produce massive information every day and save it in the form of pictures and videos. This thesis investigates the factors that affect the judgment of the equipment of multimedia information shooting and some methods that can help to improve the accuracy of judgment, such as whether the original image is uploaded to social media through splicing, scaling, scanning compression and other processing methods, and analyzes whether the original judgment result will be affected after the original image is uploaded to social media through splicing, zooming, scanning compression, etc. The results show that the method of comparing with the image to be verified is feasible. The influence of nonlinear processing methods such as HDR and anti jitter mode of the camera setting on the experimental results is also explored. In the experiment, we found that turning on the anti jitter mode, stitching and clipping the images will lead to the experimental results not achieve the expected results. Therefore, we also designed to take the average frame to reduce noise, and use the same algorithm for lossy scaling comparison to improve the accuracy. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 5657.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 2.49 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/200/11181