摘要:
Nowadays copyright infringement and data piracy are major serious concerns. Thousands of videos are being uploaded to the internet and are shared every day. Out of these videos, considerable numbers of videos are illegal copies or some videos are manipulated versions of existing media. Due to these reasons copyright management on the internet becomes a complicated process. To detect such kind of infringements, there are two approaches. First is based on watermarking and other is based on content-based copy detection (CBCD). Video copy detection system relies on a fingerprint extraction algorithm. The fingerprint extraction algorithm extracts compact content- based signatures from special images constructed from the video. Each such image represents a short segment of the video and contains temporal as well as spatial information about the video segment. These images are denoted by temporally informative representative images. Existing video fingerprint extraction algorithms have certain limitations. Therefore temporally informative representative images- discrete cosine transform (TIRI-DCT) is developed. TIRI-DCT is based on temporally informative representative images which contains spatial and temporal information of a short segment of a video sequence.
展开