DNN Based Moth Search Optimization for Video Forgery Detection
Malle Raveendra1, K Nagi reddy2

1Malle Raveendra, Ph. D Scholar in Electronics and Communication Engineering, Jawaharlal Nehru Technological University, Anantapuramu, (Andhra Pradesh), India.
2Dr.K Nagi Reddy, Professor in Electronics and Communication Engineering NBKR Institute of Science and Technology, (Andhra Pradesh), India.
Manuscript received on September 12, 2019. | Revised Manuscript received on October 15, 2019. | Manuscript published on October 30, 2019. | PP: 1190-1199 | Volume-9 Issue-1, October 2019 | Retrieval Number: A9517109119/2019©BEIESP | DOI: 10.35940/ijeat.A9517.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Recently, video tampering process becomes easier due to the rapid advancements in user-friendly editing software and multimedia technology (e.g., Mokey by Imagineer Systems, and Photoshop and Premiere by Adobe). This technologies may highly tamper the original videos, so that the audience gets mislead. Nowadays, MPEG-4 codec is included in a large proportions of video cameras and surveillance systems. Therefore the double compression detection process included as an initial step in the video forensic is receiving a high significance. In this paper, the double compression artifacts is detected by adopting the Markov based features, which identifies the interpolated original videos. The double compressed frames are then segmented by introducing an SLIC super pixel segmentation technique. Here, the feature extraction is performed by applying the scale information that is obtained from the multi-scale Gabor filters. The features of this Gabor scale accurately extract the structural features and also reduce too much of redundancy. This extracted features are then provided to DNN (deep neural network) for forgery detection. In this video forensic process, DNN classifier is included for forgery detection. The CNN classifier is included in various existing forgery detection techniques. But, in our work we include DNN because it contains number of hidden layers which provide accurate results for this forgery detection process. To improve the DNN performance, Moth Search Optimization (MSO) algorithm is introduced in this forgery detection technique. Every nook and corner of this world we can able to find the surveillance cameras for security purpose. But, some fraudsters perform forgeries in this recorded videos for their own benefits. To identify this, a lot of forgery detection techniques are coming into existence. So in this work, we introduce the DNN based MSO to perform the forgery detection in videos. This implementation is processed in python simulation platform. The parametric evaluations are taken in terms of F1- Score, average accuracy, Precision, Recall and. Experimental results will provide improved performance in video forgery detection.
Keywords: Video forgery, Markov statistics, Multi-scale Gabor filter, DNN, Moth Search Optimization (MSO), SLIC super pixel segmentation.