Biometric Face Recognition System Leads to First Arrest

The Sagem Morpho MorphoFace Investigate (MFI) system has scored its first arrest in Pierce County, Washington. The Pierce County Sheriff’s Department used the MFI biometric facial recognition application to identify a suspect by comparing an automatic teller machine (ATM) photograph against the department’s digital database of 350,000 mug shots.

Sagem Morpho’s MFI is a robust and scalable facial recognition application that includes case evidence management, biometric matching, and forensic evaluation tools for investigative and crime solving tasks. The automated system enables law enforcement and intelligence analysts to quickly compare photographs of suspects against large databases of images, such as mug shot, driver’s license, or terrorist watch lists, and make identifications within seconds.

Located in the Seattle Metropolitan area, the Pierce County Sheriff’s Department (PCSD) became the first law enforcement agency in the United States to deploy the MFI system as part of a pilot initiated in summer 2008. In the booking process, PCSD uses an Automated Fingerprint Identification System (AFIS) to check if a suspect is in its criminal database and then fingerprint examiners to validate the results. The addition of the facial recognition tool for mug shot comparison allows PCSD to validate biometric identifications with a single examiner, reducing demands on staff and speeding the overall process.

“[MFI] eliminates 80 to 85 percent of the work in booking repeat offenders,” said Steve Wilkins, PCSD Forensic Investigations Manager. “Within minutes, the criminal record can be updated.”
PCSD took the MFI application a step further in September to help break up a local identity theft ring that had been stealing ATM cards and using them to withdraw money from the victims’ bank accounts. The only evidence obtained by detectives was a grainy photograph taken of a suspect by an ATM camera during one of the fraudulent transactions. Despite the poor quality of the photo, MFI searched the 350,000-mug shot digital database and returned two possible matches in less than 5 seconds.