FPGA-based IP cores implementation for face recognition using dynamic partial reconfiguration

Afandi Ahmad, Abbes Amira, Paul Nicholl, Benjamin Krill

Research output: Contribution to journalArticle

Abstract

This paper presents a combination of novel feature vectors construction approach for face recognition using discrete wavelet transform (DWT) and field programmable gate array (FPGA)-based intellectual property (IP) core implementation of transform block in face recognition systems. Initially, four experiments have been conducted including the DWT feature selection and filter choice, features optimisation by coefficient selections and feature threshold. To examine the most suitable method of feature extraction, different wavelet quadrant and scales have been evaluated, and it is followed with an evaluation of different wavelet filter choices and their impact on recognition accuracy. In this study, an approach for face recognition based on coefficient selection for DWT is presented, and the significant of DWT coefficient threshold selection is also analysed. For the hardware implementation, two architectures for two-dimensional (2-D) Haar wavelet transform (HWT) IP core with transpose-based computation and dynamic partial reconfiguration (DPR) have been synthesised using VHDL and implemented on Xilinx Virtex-5 FPGAs. Experimental results and comparisons between different configurations using partial and non-partial reconfiguration processes and a detailed performance analysis of the area, power consumption and maximum frequency are also discussed in this paper.
Original languageEnglish
Pages (from-to)327-340
Number of pages14
JournalJournal of Real-Time Image Processing
Volume8
Issue number3
DOIs
Publication statusPublished - 2013
Externally publishedYes

Fingerprint

Discrete wavelet transforms
Face recognition
Field programmable gate arrays (FPGA)
Feature extraction
Computer hardware description languages
Wavelet transforms
Electric power utilization
Hardware
Intellectual property core
Experiments

Keywords

  • Field programmable gate array (FPGA)
  • Face recognition
  • Discrete wavelet transform (DWT)
  • Dynamic partial reconfiguration (DPR)

Cite this

Ahmad, Afandi ; Amira, Abbes ; Nicholl, Paul ; Krill, Benjamin. / FPGA-based IP cores implementation for face recognition using dynamic partial reconfiguration. In: Journal of Real-Time Image Processing. 2013 ; Vol. 8, No. 3. pp. 327-340.
@article{02cf7c064c1445568dee87afc08c7169,
title = "FPGA-based IP cores implementation for face recognition using dynamic partial reconfiguration",
abstract = "This paper presents a combination of novel feature vectors construction approach for face recognition using discrete wavelet transform (DWT) and field programmable gate array (FPGA)-based intellectual property (IP) core implementation of transform block in face recognition systems. Initially, four experiments have been conducted including the DWT feature selection and filter choice, features optimisation by coefficient selections and feature threshold. To examine the most suitable method of feature extraction, different wavelet quadrant and scales have been evaluated, and it is followed with an evaluation of different wavelet filter choices and their impact on recognition accuracy. In this study, an approach for face recognition based on coefficient selection for DWT is presented, and the significant of DWT coefficient threshold selection is also analysed. For the hardware implementation, two architectures for two-dimensional (2-D) Haar wavelet transform (HWT) IP core with transpose-based computation and dynamic partial reconfiguration (DPR) have been synthesised using VHDL and implemented on Xilinx Virtex-5 FPGAs. Experimental results and comparisons between different configurations using partial and non-partial reconfiguration processes and a detailed performance analysis of the area, power consumption and maximum frequency are also discussed in this paper.",
keywords = "Field programmable gate array (FPGA), Face recognition, Discrete wavelet transform (DWT), Dynamic partial reconfiguration (DPR)",
author = "Afandi Ahmad and Abbes Amira and Paul Nicholl and Benjamin Krill",
year = "2013",
doi = "10.1007/s11554-011-0221-x",
language = "English",
volume = "8",
pages = "327--340",
journal = "Journal of Real-Time Image Processing",
issn = "1861-8200",
publisher = "Springer-Verlag",
number = "3",

}

FPGA-based IP cores implementation for face recognition using dynamic partial reconfiguration. / Ahmad, Afandi; Amira, Abbes; Nicholl, Paul; Krill, Benjamin.

In: Journal of Real-Time Image Processing, Vol. 8, No. 3, 2013, p. 327-340.

Research output: Contribution to journalArticle

TY - JOUR

T1 - FPGA-based IP cores implementation for face recognition using dynamic partial reconfiguration

AU - Ahmad, Afandi

AU - Amira, Abbes

AU - Nicholl, Paul

AU - Krill, Benjamin

PY - 2013

Y1 - 2013

N2 - This paper presents a combination of novel feature vectors construction approach for face recognition using discrete wavelet transform (DWT) and field programmable gate array (FPGA)-based intellectual property (IP) core implementation of transform block in face recognition systems. Initially, four experiments have been conducted including the DWT feature selection and filter choice, features optimisation by coefficient selections and feature threshold. To examine the most suitable method of feature extraction, different wavelet quadrant and scales have been evaluated, and it is followed with an evaluation of different wavelet filter choices and their impact on recognition accuracy. In this study, an approach for face recognition based on coefficient selection for DWT is presented, and the significant of DWT coefficient threshold selection is also analysed. For the hardware implementation, two architectures for two-dimensional (2-D) Haar wavelet transform (HWT) IP core with transpose-based computation and dynamic partial reconfiguration (DPR) have been synthesised using VHDL and implemented on Xilinx Virtex-5 FPGAs. Experimental results and comparisons between different configurations using partial and non-partial reconfiguration processes and a detailed performance analysis of the area, power consumption and maximum frequency are also discussed in this paper.

AB - This paper presents a combination of novel feature vectors construction approach for face recognition using discrete wavelet transform (DWT) and field programmable gate array (FPGA)-based intellectual property (IP) core implementation of transform block in face recognition systems. Initially, four experiments have been conducted including the DWT feature selection and filter choice, features optimisation by coefficient selections and feature threshold. To examine the most suitable method of feature extraction, different wavelet quadrant and scales have been evaluated, and it is followed with an evaluation of different wavelet filter choices and their impact on recognition accuracy. In this study, an approach for face recognition based on coefficient selection for DWT is presented, and the significant of DWT coefficient threshold selection is also analysed. For the hardware implementation, two architectures for two-dimensional (2-D) Haar wavelet transform (HWT) IP core with transpose-based computation and dynamic partial reconfiguration (DPR) have been synthesised using VHDL and implemented on Xilinx Virtex-5 FPGAs. Experimental results and comparisons between different configurations using partial and non-partial reconfiguration processes and a detailed performance analysis of the area, power consumption and maximum frequency are also discussed in this paper.

KW - Field programmable gate array (FPGA)

KW - Face recognition

KW - Discrete wavelet transform (DWT)

KW - Dynamic partial reconfiguration (DPR)

U2 - 10.1007/s11554-011-0221-x

DO - 10.1007/s11554-011-0221-x

M3 - Article

VL - 8

SP - 327

EP - 340

JO - Journal of Real-Time Image Processing

JF - Journal of Real-Time Image Processing

SN - 1861-8200

IS - 3

ER -