FPGA implementation of CMF for embedded palm biometric system

Author

Pudzs, Mihails ; Fuksis, R. ; Ruskuls, Rinalds ; Barkans, Davis ; Eglitis, Teodors ; Greitans, Modris

Author_Institution

Inst. of Electron. & Comput. Sci., Riga, Latvia

fYear

2013

fDate

9-13 Sept. 2013

Firstpage

1

Lastpage

5

Abstract

Most multimodal palm biometric systems are still PC-based, because of the complicated image processing algorithms necessary to process biometric data. In this paper we demonstrate how to implement Complex Matched Filter in FPGA based systems for real-time palmprint and palm vein image processing. CMF approach is based on matched filtering with rotated line extraction kernels, however, CMF requires less computational resources and it obtains additional angular information about the extracted biometric features. This information is valuable in feature description and recognition process. Topics that are covered in this paper include optimization of used multipliers and real-time data processing without use of external RAM resources.

Keywords

feature extraction; field programmable gate arrays; matched filters; palmprint recognition; vein recognition; CMF approach; FPGA based systems; angular information; biometric feature extraction; complex matched filter; embedded palm biometric system; feature description process; feature recognition process; multimodal palm biometric systems; multiplier; palm vein image processing; real-time data processing; real-time palmprint image processing; rotated line extraction kernels; Biometrics (access control); Feature extraction; Field programmable gate arrays; Kernel; Random access memory; Real-time systems; Vectors; FPGA; biometric system; complex matched filtering; linear filtering; resource optimization;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing Conference (EUSIPCO), 2013 Proceedings of the 21st European

Conference_Location

Marrakech

Type

conf

Filename

6811706