This new video library has been designed and built for the purpose of video forensics specifically related to camera identification and integrity verification. As far as I know, no such library or similar currently exists in the community.
The Library consists of two parts.
- Original videos used to test algorithms for camera identification, device linking.
- Forged videos used to test forgery detection algorithms
SULFA contains original as well as forged video files, which will be freely available through the dedicated website at http://sulfa.cs.surrey.ac.uk/.
There are approximately 150 videos collected from three camera sources, which are:
- Canon SX220 (codec H.264)
- Nikon S3000 (codec MJPEG)
- Fujifilm S2800HD (codec MJPEG)
Each video is approximately 10 seconds long with resolution of 320x240 and 30 frames per second. All videos have been shot after carefully considering both temporal and spatial video characteristics. In order to present life-like scenarios, various complex and simple scenes have been shot with and without using camera support (tripod). Nine original videos from each source in SULFA have been tested with Photo Response Non Uniformity (PRNU) based camera identification methods. SULFA also includes videos with cloning or copy paste forgery. Each forged video includes full information of the doctored region.