The Experts below are selected from a list of 16815 Experts worldwide ranked by ideXlab platform
Lin Shu-wei - One of the best experts on this subject based on the ideXlab platform.
-
A Study of Fingerprint Identification Technology
Computers & Security, 2010Co-Authors: Lin Shu-weiAbstract:This paper introduced the principle of Fingerprint Identification technology,and discussed both merits and limitations.
Yan Pu-liu - One of the best experts on this subject based on the ideXlab platform.
-
A Secure Platform Based on Fingerprint Identification
Computer Engineering, 2001Co-Authors: Yan Pu-liuAbstract:For the insecurity of the of cryptosystem in the security of network communication, the information's security would be intimidated. This paper presents a secure platform based on Fingerprint Identification which in some extent could improve the communication security.
Davide Maltoni - One of the best experts on this subject based on the ideXlab platform.
-
Large-scale Fingerprint Identification on GPU
Information Sciences, 2015Co-Authors: Raffaele Cappelli, Matteo Ferrara, Davide MaltoniAbstract:Abstract This paper proposes a new parallel algorithm to speed up Fingerprint Identification using GPUs. A careful design of the algorithm and data structures, guided by well-defined optimization goals, yields a speed-up of 1946× over a baseline sequential CPU implementation and of 207× over a CPU implementation optimized with SIMD instructions. The proposed algorithm enables a medium-scale AFIS (Automated Fingerprint Identification System) to run on a simple PC with four Tesla C2075 GPUs. On a benchmark with 250 000 Fingerprints and 100 000 queries, the proposed system yields state-of-the-art biometric accuracy with a throughput of more than 35 million Fingerprint matches per second. The proposed approach can be easily scaled-up, thus making possible the implementation of a large-scale AFIS (i.e., with a database of hundred million Fingerprints) on inexpensive hardware.
Mohammad S. Alam - One of the best experts on this subject based on the ideXlab platform.
-
Joint transform correlation for Fingerprint Identification
Advanced Optical and Quantum Memories and Computing, 2004Co-Authors: Mohammad S. Alam, Aed M. El-saba, El-houssine H. Horache, Srinivas RegulaAbstract:The pattern matching for Fingerprints requires a large amount of data and computation time. Practical Fingerprint Identification systems require minimal errors and ultrafast processing time to perform real time verification and Identification. By utilizing the two-dimensional processing capability, ultrafast processing speed and noninterfering communication of optical processing techniques, Fingerprint Identification systems can be implemented in real time. Among the various pattern matching systems, the joint transform correlator (JTC) has been found to be inherently suitable for real time matching applications. Among the various JTCs, the fringeadjusted JTC has been found to yield significantly better correlation output compared to alternate JTCs. In this paper, we review the latest trends and advancements in Fingerprint Identification system based on the fringeadjusted JTC. Since all pattern matching systems suffer from high sensitivity to distortions, the synthetic discriminant function concept has been incorporated in fringe-adjusted JTC to ensure distortion-invariant Fingerprint Identification. On the other hand a novel polarization-enhanced Fingerprint verification system is described where a polarized coherent light beam is used to record spatially dependent response of the scattering medium of the Fingerprint to provide detailed surface information, which is not accessible to mere intensity measurement. It is shown that polarization-enhanced database improves the accuracy of the Fingerprint Identification or verification system significantly. Keywords: Fringe-adjust joint transform correlation, finger print Identification, polarization, synthetic discriminant function
-
Real-time Fingerprint Identification
Optics & Laser Technology, 2004Co-Authors: Mohammad S. Alam, M. Akhteruzzaman, A.k. CherrriAbstract:The pattern matching for Fingerprints requires a large amount of data and computation time. Practical Fingerprint Identification systems require minimal errors and ultrafast processing time to perform real-time verification and Identification. By utilizing the two-dimensional processing capability, ultrafast processing speed and non-interfering communication of optical processing techniques, Fingerprint Identification systems can be implemented in real-time. Among the various pattern matching systems, the joint transform correlator (JTC) has been found to be inherently suitable for real-time matching applications. Among the various JTCs, the fringe-adjusted JTC has been found to yield significantly better correlation output compared to alternate JTCs. In this paper, a Fingerprint Identification system has been developed based on the fringe-adjusted JTC. Since all pattern matching systems suffer from high sensitivity to distortions, the synthetic discriminant function concept has been incorporated in fringe-adjusted JTC to ensure distortion-invariant Fingerprint Identification.
-
Polarization-based sensor for Fingerprint Identification
Optical Pattern Recognition XIV, 2003Co-Authors: Aed M. El-saba, Mohammad S. AlamAbstract:A novel polarization-based Fingerprint Identification sensor is proposed in this paper. This sensor consists of an optoelectronic system where the enrollment process is recorded optically and the Identification process is carried out digitally using the concept of fringe-adjusted joint transform correlation technique. In the optical part, a polarized coherent light beam is used to record spatially dependent response of the scattering medium of the Fingerprint to provide detailed surface information, which is not accessible to mere intensity measurement. Both simulation and experimental results are presented to evaluate the performance of the proposed technique.
-
Real time Fingerprint Identification
Proceedings of the IEEE 2000 National Aerospace and Electronics Conference. NAECON 2000. Engineering Tomorrow (Cat. No.00CH37093), 1Co-Authors: Mohammad S. Alam, M. AkhteruzzamanAbstract:The pattern matching for Fingerprints requires a large amount of data and computation time. Practical Fingerprint Identification systems require minimal errors and ultrafast processing time to perform real time verification and Identification. By utilizing the two-dimensional processing capability, fast processing speed and non-interfering communication of optical processing techniques, such extremely fast real time Fingerprint Identification systems can be implemented. Among the various pattern matching systems, the joint transform correlator (JTC) has been found to be inherently suitable for real time matching applications. Among the various JTCs the fringe-adjusted JTC has been found to yield significantly better correlation output compared to alternate JTCs. In this paper, a Fingerprint Identification system has been developed based on the fringe-adjusted JTC. Since all pattern matching systems suffer from high sensitivity to distortions, the synthetic discriminant function concept has been incorporated in fringe-adjusted JTC to ensure distortion-invariant Fingerprint Identification.
Raffaele Cappelli - One of the best experts on this subject based on the ideXlab platform.
-
Large-scale Fingerprint Identification on GPU
Information Sciences, 2015Co-Authors: Raffaele Cappelli, Matteo Ferrara, Davide MaltoniAbstract:Abstract This paper proposes a new parallel algorithm to speed up Fingerprint Identification using GPUs. A careful design of the algorithm and data structures, guided by well-defined optimization goals, yields a speed-up of 1946× over a baseline sequential CPU implementation and of 207× over a CPU implementation optimized with SIMD instructions. The proposed algorithm enables a medium-scale AFIS (Automated Fingerprint Identification System) to run on a simple PC with four Tesla C2075 GPUs. On a benchmark with 250 000 Fingerprints and 100 000 queries, the proposed system yields state-of-the-art biometric accuracy with a throughput of more than 35 million Fingerprint matches per second. The proposed approach can be easily scaled-up, thus making possible the implementation of a large-scale AFIS (i.e., with a database of hundred million Fingerprints) on inexpensive hardware.