Front line investigators and digital forensic examiners are encountering an ever increasing number of images in almost every investigation they perform. This exponential growth in the volume of images can challenge investigators searching for illicit online activity, Child Sexual Abuse Material (CSAM), extremist propaganda, or other types of image content.
In this short video, ADF digital forensic specialist, Rich Frawley, demonstrates ADF's digital forensic image recognition and classification capabilities.
To help investigators quickly recognize and categorize images, reduce the "noise", and focus their investigation, ADF started offering image classification in 2006, beginning with CSAM. In 2018, ADF upgraded the image classifier to use TensorFlow, the leading artificial intelligence library, and trained it to recognize a variety of visual classes relevant to its users including:
- child abuse
- scanned documents
Because image classification is time-consuming and the ADF tools are often used to quickly qualify exhibits on-scene or in the lab, the classification starts after the data collection is complete. To further save time, all pictures go through an initial filter that eliminates non-photographs (icons, clip art, and other pixel art) so only the remaining pictures are classified.
The image classifier works on all the collected pictures and videos coming from the file system, archives, databases, thumbnails, documents, emails, messages, downloads, and unallocated space. And users have the ability to select the exact confidence value to show more pictures of the same class as time permits.
In addition to image classification, the ADF products support image matching with PhotoDNA as well as MD5/SHA1 hash matching by importing VICS-compatible datasets.
If you're a member of an ICAC Task Force, we've also compiled a list of upcoming Internet Crimes Against Children training events and conferences in the United States.