Dual adaptive deep convolutional neural network for video forgery detection in 3D lighting environment

Video forgery detection is one of the challenges in this digital era, where the focus is on discovering authenticity. Though there are so many methods available to detect forgeries in the video, there is no method that utilizes illumination-based forgery detection. Hence, this research focuses on establishing the 3D model of the video frame to generate light coefficients in order to detect the forgeries in the video. On the other hand, this paper proposes dual adaptive-Taylor-rider optimization algorithm-based deep convolutional neural network (DA-Taylor-ROA-based DCNN) for video forgery detection, where DCNN is trained using the dual adaptive-Taylor-rider optimization algorithm (DA-TROA) that inherits the adaptive concept and Taylor series within the standard rider optimization algorithm (ROA). For the detection process, the distance-based features from the light coefficients and face objects detected using the Viola–Jones algorithm from the video frames are used. The significance of the method is analyzed using the real images for varying noise conditions based on the performance metrics, such as accuracy, true positive rate, and true negative rate. The percentage improvement of accuracy for proposed DA-Taylor-ROA-based DCNN with respect to Taylor-ROA-Based deep CNN is 4.3626% in the absence of noise, and 1.5985% of accuracy improvement in the presence of speckle noise, respectively.

[1]  Hany Farid,et al.  Exposing Digital Forgeries Through Specular Highlights on the Eye , 2007, Information Hiding.

[2]  K. Alagarsamy,et al.  Taylor Series Prediction of Time Series Data with Error Propagated by Artificial Neural Network , 2014 .

[3]  Károly Héberger,et al.  Life beyond the Tanimoto coefficient: similarity measures for interaction fingerprints , 2018, Journal of Cheminformatics.

[4]  Nasir D. Memon,et al.  Digital Forensics , 2009, IEEE Secur. Priv..

[5]  Khurshid Asghar,et al.  Spatial Video Forgery Detection and Localization using Texture Analysis of Consecutive Frames , 2019, Advances in Electrical and Computer Engineering.

[6]  Jing Dong,et al.  Optimized 3D Lighting Environment Estimation for Image Forgery Detection , 2017, IEEE Transactions on Information Forensics and Security.

[7]  Min Wu,et al.  Digital forensics [From the Guest Editors] , 2009 .

[8]  Hany Farid,et al.  Exposing digital forgeries from 3-D lighting environments , 2010, 2010 IEEE International Workshop on Information Forensics and Security.

[9]  Tianqiang Huang,et al.  A video forgery detection algorithm based on compressive sensing , 2014, Multimedia Tools and Applications.

[10]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[11]  Sanjay Jain,et al.  Tampering detection and localization in digital video using temporal difference between adjacent frames of actual and reconstructed video clip , 2020 .

[12]  Yuesheng Zhu,et al.  A detection method for facial expression reenacted forgery in videos , 2018, International Conference on Digital Image Processing.

[13]  Anderson Rocha,et al.  Image Splicing Detection Through Illumination Inconsistencies and Deep Learning , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[14]  Kulbir Singh,et al.  Video frame and region duplication forgery detection based on correlation coefficient and coefficient of variation , 2018, Multimedia Tools and Applications.

[15]  Hewa Majeed Zangana,et al.  Detection clone an object movement using an optical flow approach , 2018, 2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE).

[16]  Shahrokh Ghaemmaghami,et al.  Detection of regional copy/move forgery in MPEG videos using optical flow , 2015, 2015 The International Symposium on Artificial Intelligence and Signal Processing (AISP).

[17]  D. Binu,et al.  RideNN: A New Rider Optimization Algorithm-Based Neural Network for Fault Diagnosis in Analog Circuits , 2019, IEEE Transactions on Instrumentation and Measurement.

[18]  Wei Zhang,et al.  Detecting Removed Object from Video with Stationary Background , 2012, IWDW.

[19]  K. Sitara,et al.  Differentiating synthetic and optical zooming for passive video forgery detection: An anti-forensic perspective , 2019, Digit. Investig..

[20]  Ghazali Sulong,et al.  Detection of copy-move image forgery based on discrete cosine transform , 2016, Neural Computing and Applications.

[21]  Zhang Xiong,et al.  3D lighting-based image forgery detection using shape-from-shading , 2012, 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO).

[22]  Vipin Tyagi,et al.  Image Forgery Detection: Survey and Future Directions , 2019, Data, Engineering and Applications.

[23]  Cuihua Li,et al.  A novel passive forgery detection algorithm for video region duplication , 2018, Multidimens. Syst. Signal Process..

[24]  Hany Farid,et al.  Detecting Photographic Composites of People , 2008, IWDW.

[25]  Thomas Vetter,et al.  A morphable model for the synthesis of 3D faces , 1999, SIGGRAPH.

[26]  Ahmad Faraahi,et al.  DWT-DCT (QCD) based copy-move image forgery detection , 2011, 2011 18th International Conference on Systems, Signals and Image Processing.

[27]  Bo Peng,et al.  Improved 3D lighting environment estimation for image forgery detection , 2015, 2015 IEEE International Workshop on Information Forensics and Security (WIFS).

[28]  Qingzhong Liu,et al.  Detect Video Forgery by Performing Transfer Learning on Deep Neural Network , 2019, ICNC-FSKD.

[29]  Leibo Liu,et al.  Deep Convolutional Neural Network Architecture With Reconfigurable Computation Patterns , 2017, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[30]  Sonja Grgic,et al.  CoMoFoD — New database for copy-move forgery detection , 2013, Proceedings ELMAR-2013.