Software giant Microsoft and researchers from a South Korean university have announced two new methods that can be used to auto-detect pornographic movies and images, a report on the Think Digit website said.

Microsoft said they will be using a technology, PhotoDNA, which will be used to scan Facebook, SkyDrive and Bing for child pornography. The project will be undertaken in association with the National Center for Missing and Exploited Children, a private, non-profit organization established in 1984 by the United States Congress.

If the scan detects any inappropriate image it will be deleted immediately, and the uploader will be prosecuted by the authorities. Facebook will scrutinize every image that will be uploaded and compare it against a database of child porn digital fingerprints and will not accept any exploitative images.

Meanwhile, two researchers at Advanced Institute of Science and Technology, Daedeok Innopolis, Daejeon in South Korea have used the Radon transform signal which processes a technique to detect sexual scream or moan in video files.

The Korean researchers, during the project, found that while speech is low-pitched and music is variable, the pornographic sounds are generally high-pitched, periodically repeat and change tone rapidly. The technique showed 93 per cent success rate.

PhotoDNA can precisely identify images that have been considerably resized or cropped, and, after extensive testing, the technology is yet to provide any false results, the report said.

PhotoDNA’s only setback, however, is that it is unable to decide if an image is pornographic but can match it against known samples of child porn.