[Paper] Fuzzy Commitment Scheme-Based Secure Identification for JPEG XR Images under Various Compression Ratios

Abstract

A secure identification scheme for JPEG XR images is proposed in this paper.The aim is to securely identify JPEG XR images which are generated from the same original image under various compression levels. The positive and negative signs of lapped biorthogonal transform coefficients are used as features.The proposed scheme is robust against a difference in compression levels, and does not produce false negative matches in any compression level. In addition, to construct a secure identification system, we propose a novel identification system that consists of an error correction technique and a fuzzy commitment scheme, which is a well-known biometric cryptosystem. There is no existing scheme having these properties for JPEG XR images. Moreover, a way for speeding up the identification is also proposed. The experimental results show the proposed scheme is effective for identifying JPEG XR images in terms of true positive matches.

Performance analysis of JPEG XR with deep learning-based image super-resolution

“…In this step, core transform is performed twice. Finally, QP is used to perform quantization and then performs the entropy encoding [12]. During the encoding process, the quantization parameter greater than one makes the model lossy compression, and the output image contains degradation artifacts.…”