Integrating Faces and Fingerprints for Personal Identification
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Multichannel Approach to Fingerprint Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence
Performance Evaluation of Fingerprint Verification Systems
IEEE Transactions on Pattern Analysis and Machine Intelligence
Alpha---Beta bidirectional associative memories: theory and applications
Neural Processing Letters
IEEE Transactions on Computers
A new model of BAM: alpha-beta bidirectional associative memories
ISCIS'06 Proceedings of the 21st international conference on Computer and Information Sciences
A novel approach to automatic color matching
CIARP'06 Proceedings of the 11th Iberoamerican conference on Progress in Pattern Recognition, Image Analysis and Applications
Alpha-Beta associative memories for gray level patterns
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
FPGA-Based architecture for extended associative memories and its application in image recognition
MICAI'12 Proceedings of the 11th Mexican international conference on Advances in Artificial Intelligence - Volume Part I
Hi-index | 0.00 |
Associative memories have a number of properties, including a rapid, compute efficient best-match and intrinsic noise tolerance that make them ideal for many applications. However, a significant bottleneck to the use of associative memories in real-time systems is the amount of data that requires processing. Notwithstanding, Alpha-Beta Associative Memories have been widely used for color matching in industrial processes [1], text translation [2] and image retrieval applications [3]. The aim of this paper is to present the work that produced a dedicated hardware design, implemented on a field programmable gate array (FPGA) that applies the Alpha-Beta Associative Memories model for fingerprint verification tasks. Along the experimental phase, performance of the proposed associative memory architecture is measured by learning large sequences of symbols and recalling them successfully. As a result, a simple but efficient embedded processing architecture that overcomes various challenges involved in pattern recognition tasks is implemented on a Xilinx Spartan3 FPGA.