Using SVM and KNN to Evaluate Performance Based on Video Plagiarism Detectors and Descriptors for Global Features

Abstract

The detection of video piracy has improved and emerged as a popular issue in the field of digital video copyright protection because a sequence of videos often comprises a huge amount of data. The major difficulty in achieving efficient and simple video copy detection is to identify compressed and exclusionary video characteristics. To do this, we describe a video copy detection strategy that created the properties for a spatial-temporal domain. The first step is to separate each video sequence into the individual video frame, and then extract the boundaries of each video frame by using PCA SIFT and Hessian- Laplace. Next, for each video frame, we have to implement SVM and KNN features in the spatial and temporal domains to measure their performance matrices in the feature extraction. Finally, the global features found in the Video copy detection are accomplished uniquely and efficiently. Experiments arranged a commonly used VCDB 2014 video dataset, showing that result. The proposed approach is based on various copy detection algorithms and shows various features in terms of both accuracy and efficiency.