Video Forgery Detection Based on Non-Subsampled Contourlet Transform and Gradient Information

摘要

For digital video, object-based manipulations, such as adding, removing or changing objects, are usually malicious tamper/forgery operations. Compared with the conventional double compression or frame-based operation, it makes more sense to detect these object-based manipulations because they might directly affect video content. This paper concentrates on video object contour and its Adjustable Width Object Boundary (AWOB), digs the trace of forgery in small-scale by analysing detail coefficients of Non-Subsampled Contourlet (NSCT) and gradient information, of which feature vectors are obtained and combined as the input of Support Vector Machine (SVM), thus natural objects and forged ones will be successfully classified. The proposed algorithm turns out to be effective with a high accuracy of correct detection up to 95%.