Detecting Double Mixed Compressed Images Based on Quaternion Convolutional Neural Network  

作　　者：Hao WANG Jinwei WANG Xuelong HU Bingtao HU Qilin YIN Xiangyang LUO Bin MA Jinsheng SUN 

机构地区：[1]Department of Automation,Nanjing University of Science and Technology,Nanjing 210044,China [2]Engineering Research Center of Digital Forensics,Ministry of Education,Nanjing 210044,China [3]Department of Computer and Software,Nanjing University of Information Science and Technology,Nanjing 210044,China [4]School of Management,Nanjing University of Posts and Telecommunications,Nanjing 210044,China [5]Department of Computer Science and Engineering,Guangdong Province Key Laboratory of Information Security Technology,Sun Yat-sen University,Guangzhou 510006,China [6]State Key Laboratory of Mathematical Engineering and Advanced Computing,Zhengzhou 450001,China [7]Qilu University of Technology,Jinan 250353,China

出　　处：《Chinese Journal of Electronics》2024年第3期657-671,共15页电子学报（英文版）

基　　金：supported by the National Natural Science Foundation of China (Grant Nos.62072250,61772281,61702235,U1636117,and U1804263)。

摘　　要：Detection of color images that have undergone double compression is a critical aspect of digital image forensics.Despite the existence of various methods capable of detecting double Joint Photographic Experts Group(JPEG)compression,they are unable to address the issue of mixed double compression resulting from the use of different compression standards.In particular,the implementation of Joint Photographic Experts Group 2000(JPEG2000)as the secondary compression standard can result in a decline or complete loss of performance in existing methods.To tackle this challenge of JPEG+JPEG2000 compression,a detection method based on quaternion convolutional neural networks(QCNN)is proposed.The QCNN processes the data as a quaternion,transforming the components of a traditional convolutional neural network(CNN)into a quaternion representation.The relationships between the color channels of the image are preserved,and the utilization of color information is optimized.Additionally,the method includes a feature conversion module that converts the extracted features into quaternion statistical features,thereby amplifying the evidence of double compression.Experimental results indicate that the proposed QCNN-based method improves,on average,by 27%compared to existing methods in the detection of JPEG+JPEG2000 compression.

关 键 词：Color image forensics JPEG JPEG2000 Mixed double compression Quaternion convolutional neural network 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]