Robust Video Copy Detection System

The video copy detection system based on content fingerprinting, is used for video indexing and copyright applications. This system consists of two algorithms: a fingerprint extraction algorithm succeeded by a fast approximate search algorithm. The first algorithm extracts compact content-based signatures from the images captured from the query video. Each such image signifies a short sector of the input video and contains temporal as well as spatial information about the video sector. These images are denoted by temporally informative representative images. To find whether a query video (or a part of it) is copied from a video in a system database, fingerprints of all the existing videos in the system database are extracted and kept in advance. The search algorithm searches the retrieved fingerprints to find matches for the fingerprints of the input video. The proposed approximate and quick search algorithm facilitates the online application of the system to a large video database of tens of millions of fingerprints, so that a match (if it exists) is found in a few seconds.