Automated Human Image Detection and Authentication

This project will develop software to assist computer forensic specialists in cases that involve searching for images of humans, such as victims of child pornography. Current state of the art technology requires that a forensic specialist manually sift through the potentially hundreds of thousands of images that are often found on a seized harddrive. The software from this project will automatically detect high concentrations of skin tones in image files and mark those image files for subsequent manual investigation. It will also assign a probability that the image file was computer-generated, which is an essential element in the authentication of evidence in child pornography cases. The software from this project will be integrated into Guidance Software's EnCase forensic toolkit to provide an easy-to-use interface that will initiate the automated human image detection and authentication software module.

ca/ncf