Parallel Algorithms for an
Automated Fingerprint Image Comparison System
Parallel Algorithms for an Automated
Fingerprint Image Comparison System
International Symp. on Parallel and Distributed Processing (SPDP'96), IEEE Computer Soc.,
Oct. 1996
(PDF file,220k)
This paper addresses the problem of developing effcient parallel algorithms for the
training procedure of a neural network based Fingerprint Image Comparison (FIC) system.
The target architecture is assumed to be a coarse-grain distributed memory parallel
architecture. Two types of parallelism: node parallelism and training set parallelism
(TSP) are investigated. Theoretical analysis and experimental results show that node
parallelism has low speedup and poor scalability, while TSP proves to have the best
speedup performance. TSP, however, is amenable to a slow convergence rate. In order to
reduce this effect, a modifed training set parallel algorithm using weighted contributions
of synaptic connections is proposed. Experimental results show that this algorithm
provides a fast convergence rate, while keeping the best speedup performance obtained.
Implementation of a Training Set Parallel
Algorithm for an Automated Fingerprint Image Comparison System
International Conf. on Parallel Processing(ICPP'96), IEEE Computer Soc., Aug. 1996
(PDF file,116k)
This paper addresses the problem of implementing a training set parallel algorithm (TSPA)
for the training procedure of a neural network based Fingerprint Image Comparison (FIC)
system. Experimental results on a 32 node CM-5 system show that TSPA achieves almost
linear speedup performance. This parallel algorithm is applicable to ANN training in
general and is not dependent on the ANN architecture.