Improving long range and high magnification face recognition: Database acquisition, evaluation, and enhancement

• Published in: Computer vision and image understanding Vol. 111; no. 2; pp. 111 - 125
• Main Authors: Yao, Yi, Abidi, Besma R., Kalka, Nathan D., Schmid, Natalia A., Abidi, Mongi A.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Inc 01.08.2008; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Computer science; control theory; systems; Exact sciences and technology; Face database; Face recognition; Image enhancement; Image quality; Image restoration; Information systems. Data bases; Long range surveillance; Memory organisation. Data processing; Pattern recognition. Digital image processing. Computational geometry; Software; Super-resolution; Image quality; Super-resolution; Face recognition; Long range surveillance; Face database; Image restoration; Image enhancement; Biometrics; High resolution; Adaptive algorithm; Image processing; Noise reduction; Outdoor installation; Video databases; Indoor installation; Facies; Database; Magnification; Monitoring; Computer vision; Image databank; Pattern recognition; Blurred image; Surveillance; Authentication; Signal to noise ratio
• ISSN: 1077-3142; 1090-235X
• DOI: 10.1016/j.cviu.2007.09.004

In this paper, we describe a face video database, UTK-LRHM, acquired from long distances and with high magnifications. Both indoor and outdoor sequences are collected under uncontrolled surveillance conditions. To our knowledge, it is the first database to provide face images from long distances (indoor: 10–16 m and outdoor: 50–300 m). The corresponding system magnifications range from 3× to 20× for indoor and up to 284× for outdoor. This database has applications in experimentations with human identification and authentication in long range surveillance and wide area monitoring. Deteriorations unique to long range and high magnification face images are investigated in terms of face recognition rates based on the UTK-LRHM database. Magnification blur is shown to be a major degradation source, the effect of which is quantified using a novel blur assessment measure and alleviated via adaptive deblurring algorithms. A comprehensive processing algorithm, including frame selection, enhancement, and super-resolution is introduced for long range and high magnification face images with a large variety of resolutions. Experimental results using face images of the UTK-LRHM database demonstrate a significant improvement in recognition rates after assessment and enhancement of degradations.