The effects of varying illumination levels on FRS algorithm performance
Eric P. Kukula, Stephen Elliot · Annual Information Security Symposium · 2004
This study evaluated the performance of a commercially available face recognition algorithm for the verification of an individual's identity pertaining to three enrollment illumination levels. Existing face recognition technology from still or video sources is becoming a practical tool for law enforcement, security, and counter-terrorist applications despite the limitations of the current technology. This evaluation examined the influence of variations in illumination levels on the performance of a face recognition algorithm, specifically testing the significance between verification attempts and enrollment conditions with respect to factors of age, gender, ethnicity, facial characteristics, and facial obstructions. The failure to enroll (FTE) rates from the low illuminance (7-12 lux), medium illuminance (407 - 412 lux) and high illuminance (800 - 815 lux) enrollments were 6.25%, 3.22%, and 1.09% respectively, while the failure to acquire (FTA) rates were 0.92%, 0.65%, and 0.00%. The results of the evaluation showed that for low and medium illuminance enrollments there was a statistically significant difference between verification attempts made at low, medium, and high illuminance at α= 0.01. However for the high illuminance enrollment, there was no statistically significant difference between verification attempts made at low, medium or high illuminance at α= 0.01.