A New Forgery Image Dataset and its Subjective Evaluation
Hossain, F., Dagiuklas, T and Skodras, A. (2023). A New Forgery Image Dataset and its Subjective Evaluation. 2023 IEEE IAS Global Conference on Emerging Technologies (GlobConET). London 19 - 21 May 2023 IEEE. https://doi.org/10.1109/globconet56651.2023.10150020
|Authors||Hossain, F., Dagiuklas, T and Skodras, A.|
The aim of this research paper is to present a new forgery image dataset with a thorough subjective evaluation in detecting manipulated images, considering various parameters. The original images were obtained from public sources, and meaningful forgeries were produced using an image editing plat- form with three techniques: cut-paste, copy-move, and erase-fill. Both pre-processing and post-processing methods were used to generate fake images. The subjective evaluation revealed that the accuracy of manipulated image detection was affected by various factors, such as user type, image quantity, tampering method, and image resolution, which were analyzed using quantitative data.
|Keywords||Forgery Image Dataset; Image Manipulation; Subjective Assessment; Tampering Detection|
|Digital Object Identifier (DOI)||https://doi.org/10.1109/globconet56651.2023.10150020|
|Accepted author manuscript|
File Access Level
|19 May 2023|
|Publication process dates|
|Deposited||07 Jul 2023|
Copyright © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
2views this month
0downloads this month