6533b82bfe1ef96bd128dee2

RESEARCH PRODUCT

Design and Implementation of a Low-cost Embedded Iris Recognition System on a Dual-core Processor Platform

Hamid Reza KarimiJiangyuan MeiYulin SiYulin SiHuijun GaoChuan Wang

subject

Multi-core processorbusiness.industryComputer scienceFeature extractionIris recognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONNormalization (image processing)SegmentationIRIS (biosensor)General MedicinebusinessDigital signal processingComputer hardware

description

Abstract Design of a low-cost embedded iris recognition system is described in this paper. Firstly, we develop a simple and effective iris image acquisition unit, which is cheap and easy to use. This is achieved by both of hardware design and image evaluation algorithm development. Secondly, the iris recognition algorithm is introduced, including iris segmentation, image normalization, feature extraction, and code matching. The algorithm implementation architecture is based on an embedded dual-core processor platform, Texas Instruments TMS320DM6446 evaluation module (Davinci), which contains an ARM core and a DSP core in one chip. Thirdly, the evaluation experiments are performed on the established iris database, and the experimental results suggest that the system shows good performance both on accuracy and efficiency.

yearjournalcountryeditionlanguage
2012-01-01IFAC Proceedings Volumes
https://doi.org/10.3182/20120403-3-de-3010.00063