Learning based video authentication using statistical local information

With the innovations and development in sophisticated video editing technology, it is becoming increasingly significant to assure the trustworthiness of video information. Today digital videos are also increasingly transmitted over non secure channels such as Internet. Therefore in surveillance, medical and various other fields, video contents must be protected against attempt to manipulate them. This paper presents an intelligent video authentication algorithm using support vector machine, which is a non-linear classifier. The proposed algorithm does not require the computation and storage of any secret key or embedding of any watermark. It computes the local information of the difference frames of given video statistically and classifies the video as tampered or non-tampered. It covers both kinds of tampering attacks, spatial and temporal. It uses a database of more than 4000 tampered and non-tampered video frames and gives excellent results with 99.12 classification accuracy.