• Rohini Sawant
• Manoj Sabnis

The consumption and utilization of Multimedia in different digital formats is increasing across the globe. The Videos provide immediate and substantial visual and communicational opportunities than any other form of digital media. Thus with it’s proliferate use, the chances of its misuse also increase. The Video forgeries are largely affecting the videos available online and offline. A forgery of a single visual element may lead to severe misrepresentation and misunderstanding of the underlying data. Thus detecting video forgeries is of utmost importance in the current scenario. This paper suggests the detection of copy paste forgery using motion and machine learning concepts. This paper concentrates on Motion-Based Multiple Object Tracking, analysis feature coefficients of HOG, Blurriness and Chromaticity, of which feature vectors are generated and given as an input to Support Vector Machine(SVM) for classification as Forged and Original.

Video Forgery, Object Tracking, HOG, Blurriness, Chromaticity, Support Vector Machine

"MAHINE LEARNING BASED COPY MOVE VIDEO FORGERY DETECTION ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 3, page no.285-288, March-2019, Available :http://www.jetir.org/papers/JETIRAL06061.pdf

"MAHINE LEARNING BASED COPY MOVE VIDEO FORGERY DETECTION ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 3, page no. pp285-288, March-2019, Available at : http://www.jetir.org/papers/JETIRAL06061.pdf