Fully hardwired illumination invariant face recognition engine and FPGA implementation

Author

Hyuk Kim ; Miyoung Lee ; Youngseok Baek ; Seongmin Kim ; Bontae Koo ; Joohyun Lee

Author_Institution

SoC Res. Dept., Electron. & Telecommun. Res. Inst., Daejeon, South Korea

fYear

2015

fDate

24-26 June 2015

Firstpage

1

Lastpage

2

Abstract

Face recognition system plays an important role in many applications such as surveillance, biometrics and security. In this paper, we present a FPGA implementation of real-time face recognition engine consists of face detection, eye detection and feature extraction/verification module. We apply Self-Quotient Image (SQI) to reduce illumination effect. Haar-AdaBoost trained classifiers are applied for face and eye detection. Linear Discriminant Analysis (LDA) and Discrete Cosine Transform (DCT) are used for face recognition. The complete system is implemented in a Xilinx Virtex-7 device. Experimental result shows that our face recognition system operates over 30 fps at 50MHz frequency for real-time applications.

Keywords

discrete cosine transforms; face recognition; feature extraction; field programmable gate arrays; image classification; learning (artificial intelligence); DCT; FPGA implementation; Haar-AdaBoost trained classifier; LDA; SQI; Xilinx Virtex-7 device; biometrics; discrete cosine transform; eye detection; face detection; face recognition engine; feature extraction; feature verification module; field programmable gate array; frequency 50 MHz; fully hardwired illumination invariance; illumination effect reduction; linear discriminant analysis; self-quotient image; surveillance; Face; Face recognition; Feature extraction; Field programmable gate arrays; Hardware; Lighting; Real-time systems; Adaboost; Discrete Cosine Transform; FPGA; Face recognition; Haar; Linear Discriminant Analysis; Self-Quotient Image;

fLanguage

English

Publisher

ieee

Conference_Titel

Consumer Electronics (ISCE), 2015 IEEE International Symposium on

Conference_Location

Madrid

Type

conf

DOI

10.1109/ISCE.2015.7177816

Filename

7177816