Large-scale fingerprint identification on GPU

作者：Cappelli Raffaele^*; Ferrara Matteo; Maltoni Davide

来源：Information Sciences, 2015, 306: 1-20.

DOI：10.1016/j.ins.2015.02.016

• Fingerprint identification
• Minutiae
• GPU
• CUDA
• SIMD
• MCC

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 x over a baseline sequential CPU implementation and of 207 x 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.

• 出版日期2015-6-10