Back to Search Start Over

Detection and Recovery of Higher Tampered Images Using Novel Feature and Compression Strategy

Authors :
Faranak Tohidi
Manoranjan Paul
Mohammad Reza Hooshmandasl
Source :
IEEE Access, Vol 9, Pp 57510-57528 (2021)
Publication Year :
2021
Publisher :
IEEE, 2021.

Abstract

Due to the availability of powerful image-editing software and the growing amount of multimedia data that is transmitted via the Internet, integrity verifications and confidentiality of the data are becoming critical issues. However, currently, the accuracy of detecting and the recovery capability of the tampered images by the existing methods through watermarking strategy is still not at the required level, especially at a higher tampered rate. This paper proposes a new blind and fragile watermarking method to detect tampering and better recovery of tampered images. To improve the quality of both the watermarked and the recovered images, a new feature extraction scheme is introduced which will produce a short but comprehensive recovery code using a new compression strategy. If a block in the image tampers, the proposed embedded feature allows the original data to be extracted for recovery. To overcome tamper coincidence, every block’s watermarked data contains not only the recovery code belonging to the block itself but also its neighbor’s data as a second layer of recovery. Various size blocks were investigated to see the performance and compare their efficiency for recovering an image after different tampering rates. The test showed the smaller block sizes may be more suitable for locating tampering, where the bigger ones are more suitable when the tampering rate is higher. The bigger block sizes in the proposed method can recover an image even after a 60% tampering rate with high quality (more than 31 dB). The experimental results prove that the proposed method can have better efficiency for detecting tampering, and recovery of the original image, compared to the relevant existing methods.

Details

Language :
English
ISSN :
21693536
Volume :
9
Database :
Directory of Open Access Journals
Journal :
IEEE Access
Publication Type :
Academic Journal
Accession number :
edsdoj.f60679798636414f873aed19f67ad2ba
Document Type :
article
Full Text :
https://doi.org/10.1109/ACCESS.2021.3072314