Semi-fragile self-recoverable watermarking scheme for face image protection. (August 2016)

• Record Type: Journal Article
• Authors: Li, Chunlei; Yang, Ruimin; Liu, Zhoufeng; Li, Jianjun; Guo, Zhenduo
• Is Part Of: Computers & electrical engineering. Volume 54(2016)
• Page Start: 484
• Page End: 493
• Publication Date: 2016-08
• Subjects: Semi-fragile -- Self-recoverable -- Tamper detection -- Face image protection -- PCA; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2016.01.026
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: PCA coefficients are used to generate information watermarks, and the authentication watermarks are generated using SVD coefficients. The embedding position is generated by a chaotic map, and it improves the security of the proposed method. Watermarks are embedded into the mid-frequency bands by using our proposed SDPQ method. Graphical abstract: Abstract: Digital watermarking based biometric images protecting has been an active research focus. In this paper, we propose a face image protection scheme based on semi-fragile self-recoverable watermarking. Authentication watermark is generated from the singular value decomposition (SVD) coefficients for each image block, and information watermark is generated from the principal component analysis (PCA) coefficients. Both of them are embedded into wavelet medium frequency coefficients by using the proposed group-based wavelet quantization method. On the authentication side, after identifying the tampered regions, the proposed method can recover the tampered face images by using the hidden information watermark. Experimental results demonstrate that the proposed watermark scheme has high localization accuracy and robustness comparing with the existing techniques, and the recovered PCA coefficients can be used to reconstruct the Eigen-face image or be directly used for recognition system.