Fractional Quaternion Zernike Moments for Robust Color Image Copy-Move Forgery Detection

• Published in: IEEE access Vol. 6; pp. 56637 - 56646
• Main Authors: Chen, Beijing, Yu, Ming, Su, Qingtang, Shim, Hiuk Jae, Shi, Yun-Qing
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Color; color image; Color imagery; Datasets; Feature extraction; Forgery; fractional Zernike moments; image forgery detection; Quaternion; Quaternions; Robustness; Signal processing; Signal processing algorithms; Transforms
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2018.2871952

In this paper, fractional Zernike moments (FrZMs) for complex signals are generalized to fractional quaternion Zernike moments (FrQZMs) for quaternion signal processing in a holistic manner by the quaternion algebra. We first present the definition of FrQZMs and an efficient implementation algorithm for speeding up the computation of FrQZMs through FrZMs of each component of the quaternion signal. The performance of the proposed FrQZMs is evaluated by considering robust color image copy-move forgery detection. The proposed robust copy-move forgery-detection algorithm considers the FrQZMs as a feature and a modified PatchMatch algorithm as a feature matching algorithm. Experimental results on two publicly available data sets (FAU and GRIP data set) have demonstrated that the proposed FrQZM-based algorithm can achieve an overall better performance than the state-of-the-art algorithms, especially in some additional operation cases.