Vol.:(0123456789) 1 3 Journal of Real-Time Image Processing https://doi.org/10.1007/s11554-019-00937-z SPECIAL ISSUE PAPER Real‑time watermark reconstruction for the identifcation of source information based on deep neural network Rishi Sinhal 1  · Irshad Ahmad Ansari 1  · Deepak Kumar Jain 2 Received: 22 March 2019 / Accepted: 7 December 2019 © Springer-Verlag GmbH Germany, part of Springer Nature 2019 Abstract A novel deep neural network-based image watermarking method is presented to identify the source of digital data that is shared/forwarded on the internet using various messenger apps. The app that is used to share/communicate the image at the very frst time is also identifed in the proposed method. The ten-digit mobile number of the source (user) and identifca- tion data of particular messenger app (i.e. WhatsApp, Snapchat, Kik, Facebook messenger, etc.) is combined to get the text watermark signal. The part of the watermark signal representing specifc mobile-based messenger application is obtained by randomizing the Walsh orthogonal codes using secret keys. To embed the watermark, the host image (shared/forwarded) is divided into blocks of equal size and then, slantlet transform is applied on each block. To get high reliability, three copies of the source information (user and app) are embedded during watermark embedding. Watermark extraction is performed using trained multilayer deep neural network. Furthermore, an optimal block selection logic is used to get improved results for real-time applications. The method is examined against various signal-processing attacks and high robustness with signifcant imperceptibility is attained. The method is also found to be fast enough for real-time applications. The prime objective of identifying the frst user (source) and the shared/forwarded status (app detection) is successfully accomplished. Keywords Real-time source detection · Watermark reconstruction · Forwarded message identifcation · App source detection · Deep neural network 1 Introduction At present, it is very common to use social media for sev- eral motives, such as to get the latest news about people, weather, state, world, political and fnancial issues, etc. or to be connected with relatives and friends, and to provide information to people, etc. Social media network is an easy and economical way to spread information among people. Various messenger applications such as WhatsApp, Hike, Facebook Messenger, Tinder, etc. have a signifcant role in sharing and redistributing the information. According to [1], approximately two billion plus smartphone users are in the world at present. Such a widespread use of smartphones helps to download, upload or forward the digital data on the same or on some other social network application [2–4]. Even it is very easy to create a digital image of anything like printed document, etc. using smartphone cameras, and then these data can be distributed to unauthorized users using the diferent number of messenger applications [5, 6]. Some- times, people misuse social network by spreading wrong or unnecessary information to attain ignoble objectives, which in turn causes political, social, economic or many other kinds of complications. In this viewpoint, it is necessary to get as much information as possible about the origin of the multimedia data and the processing that has been done on it, in terms of users, device or location [7–10]. It can help to identify the source and to stop the misuse of the social * Irshad Ahmad Ansari irshad@iiitdmj.ac.in Rishi Sinhal rishi.sinhal.jec@gmail.com Deepak Kumar Jain deepak@cqupt.edu.cn 1 Electronics and Communication Engineering, PDPM Indian Institute of Information Technology Design and Manufacturing, Jabalpur 482005, MP, India 2 Key Laboratory of Intelligent Air-Ground Cooperative Control for Universities in Chongqing, College of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, China