Police forces today regularly photograph tattoos when suspects are booked and categorize them using a biometric standard with several categories and subcategories. The U.S. Federal Bureau of Investigation (FBI) maintains a database of tattoo images as part of its Next Generation Identification Program, but searching the database can be difficult due to categorization issues and a lack of granularity. However, the FBI recently collaborated with the U.S. National Institute of Standards and Technology (NIST) to find a better way to search for matching tatoos.
Last fall, NIST issued a challenge to assess the state of the art in tattoo identification technology. Six organizations participated in the challenge: Compass Technical Consulting, the Fraunhofer Institute of Optronics, System Technologies, and Image Exploitation, the French Alternative Energies and Atomic Energy Commission, MITRE, MorphoTrak, and Purdue University. The tattoo-identification algorithms of the six organizations were required to perform five different types of searches. The six groups performed well on three of these: determining if an image contains a tattoo, identifying the same tattoo on the same person over time, and identifying a small segment of a larger tattoo. However, they performed poorly on two of the searches: identifying visually similar tattoos on different people, and searching for similar tattoos across various media.
From IEEE Spectrum
View Full Article
Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA