Quality Metrics for Practical Face Recognition
Ayman A. Abaza, Mary Ann F. Harrison, Thirimachos Bourlai · 2016
In biometric studies, quality evaluation of input data is very important, and has proven to have a direct re-lation with system performance. Quality measures can provide real-time feedback to reduce the number of poor quality submissions to the system. Another benefit is that they can predict and improve the authentication performance (e.g., by using quality-dependent thresh-olds). This paper main focus is image quality assess-ment for face recognition. First, we evaluate a num-ber of techniques that measure image quality factors namely, contrast, brightness, focus, sharpness, and il-lumination. Second, via a set of experiments measur-ing the sensitivity of each matric to quality change, we select the most practical measure(s) for each quality factor. Finally, we propose a novel face image qual-ity index (FQI) that combines the five aforementioned quality factors. Via a set of statistical significance tests, we illustrate and support that FQI is a promising qual-ity measure that can be used as an alternative to some benchmark face image quality measures. 1