ABSTRACT
A detection of fake photos is a serious concern since general users can easily create with mobile apps and computer software. In this paper, a novel method that can detect fake photos accurately is proposed. RGB color model permutations are considered and non-decimated shift-invariant wavelet transform is applied. The proposed method extracts features using the Markov process and texture operator based on co-occurrence in both the spatial and frequency domains. The feature vector dimension is reduced by using an infinite feature selection algorithm and feature selection provides quality features to improve a detection accuracy and reduce a classification model training time. The experimental analysis is performed on four photo forgery datasets and demonstrated the accuracy of the proposed scheme is outstanding for both types of forgery, splicing and copy-move when compared with previous forgery detection schemes.
Acknowledgement
This research was supported by Brain Pool program funded by the Ministry of Science and ICT through the National Research Foundation of Korea (2019H1D3A1A01101687) and Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2021R1I1A3049788).
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Funding
Notes on contributors
Saurabh Agarwal
Saurabh Agarwal received his B.E. degree in Computer Science & Engineering from Barkatullah Univerity, Bhopal in 2003 and the M.Tech degree in Software Engineering from APJ AKTU, Lucknow in 2010. He received the Ph.D. degree in Computer Engineering from University of Delhi in 2017, India. He had been employed as an assistant professor in SRMSCET, India from 2004 to 2008. Currently, he is an associate professor at Amity University, India from 2018 and works as a Korean Research Fellow at the Department of Cyber Security, Kyungil University from 2019 to 2022 and Department of Software Convergence, Andong National University from 2022, South Korea. His current research interests are image forensics and computer vision.
Ki-Hyun Jung
Ki-Hyun Jung received his B.S. degree in Computer Engineering from Kyungpook National University in 1995 and the M.S. degree in Computer Engineering from Kyungpook National University in 1997, South Korea. He received the Ph.D. degree in Computer Engineering from Kyungpook National University in 2007, South Korea. He had been employed as a senior researcher at Agency for Defense Development, South Korea from 1997 to 2003. He was a professor at the School of Computer Information, Yeungjin College, South Korea from 2003 to 2015 and the Department of Cyber Security, Kyungil University, South Korea from 2015 to 2022. Currently, he is a professor at the Department of Software Convergence, Andong National University, South Korea from 2022. His current research interests are information hiding, watermarking, steganography, steganalysis, blockchain, mobile programming, and open source intelligence.