Face Forensics announces tattoo recognition upgrade to biometric algorithm
Face Forensics has released an update to its Full Face Recognition (f2) solution which improves the program’s biometric algorithms to enable images to be matched against an existing database with higher accuracy and faster than before.
Face Forensics says that in order to respond to law enforcement community requests, f2 is now also able to identify tattoos even if they are partially obscured by clothing.
f2 is a face recognition system designed to work with embedded or linked face images in a specific SQL Server, Oracle, or DB2 database.
Once the software is fed the images, it analyzes the characteristics of each one, then uses them to generate a unique digital code describing each face.
The encrypted data is then stored in a separate database, or matching gallery, and every time a new image is added, it can be enrolled and matched against those in the gallery.
Since the search process compares encodings describing faces instead of the raw files, the searches are fast, with an average of 1 million records per second, Face Forensics says on its website.
f2 can also perform automatic enrollment of existing tattoo images in a database, automatic batch import and enrollment of tattoos in a folder, and automatic detection and encoding of new tattoos.
The tool can be used as a stand-alone solution or integrated into existing biometric-based systems, and is available as a networked application, as a .NET SDK, and as a web service.
Face Forensics has made the software available for a free evaluation by government agencies, together with full assistance and a video explaining f2’s main features.
The company also launched a forensic identification capabilities for corpses last year.