Title :
Commentary Paper on "Video Surveillance for Biometrics: Long-Range Multi-biometric System"
Author_Institution :
Comput. Sci. & Eng. Dept., Lehigh Univ., Bethlehem, PA, USA
Abstract :
This paper introduces a long-range multi-biometric system by integrating hierarchical camera system design, human detection and tracking, face detection and pose estimation, NIR laser illumination, and iris acquisition by a PTU and long focal length zoom lens. The system proposed by the paper is sound. Hierarchical design and error-correction steps are introduced in an attempt to make the system robust in real world scenarios. The main concern is two folds: the low resolution of the acquired iris images, and the processing time between frames. Low resolution iris images may lead to significantly decreased accuracy in biometric-based recognition. And the long processing time (due to detection, tracking, etc.) may prevent the system from being applicable to acquiring iris images of moving subjects.
Keywords :
biometrics (access control); error correction; image recognition; image resolution; object detection; NIR laser illumination; biometric-based recognition; error-correction; face detection; hierarchical camera system design; human detection; iris acquisition; long focal length zoom len; long-range multibiometric system; low resolution iris images; pose estimation; video surveillance; Biometrics; Cameras; Face detection; Humans; Image resolution; Iris; Lenses; Lighting; Robustness; Video surveillance;
Conference_Titel :
Advanced Video and Signal Based Surveillance, 2008. AVSS '08. IEEE Fifth International Conference on
Conference_Location :
Santa Fe, NM
Print_ISBN :
978-0-7695-3341-4
Electronic_ISBN :
978-0-7695-3422-0
DOI :
10.1109/AVSS.2008.46