A line feature extraction method for finger-knuckle-print verification

Due to its mobility and reliability, the outer finger-knuckle-print (FKP) possesses several advantages over other biometric traits of the hand. However, most existing state-of-the-art methods utilize either local features alone or together with global features for FKP verification. These methods oft...

Full description

Bibliographic Details
Main Authors: Kim, Jooyoung, Oh, Kangrok, Oh, Beom-Seok, Lin, Zhiping, Toh, Kar-Ann
Other Authors: School of Electrical and Electronic Engineering
Format: Journal Article
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/150715
_version_ 1826119112552611840
author Kim, Jooyoung
Oh, Kangrok
Oh, Beom-Seok
Lin, Zhiping
Toh, Kar-Ann
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Kim, Jooyoung
Oh, Kangrok
Oh, Beom-Seok
Lin, Zhiping
Toh, Kar-Ann
author_sort Kim, Jooyoung
collection NTU
description Due to its mobility and reliability, the outer finger-knuckle-print (FKP) possesses several advantages over other biometric traits of the hand. However, most existing state-of-the-art methods utilize either local features alone or together with global features for FKP verification. These methods often demand high computational cost despite their high verification accuracy. In this paper, we propose a novel and fast matrix projection method for extracting line features from the finger-knuckle-print for person verification. Essentially, both the horizontal and the vertical knuckle lines are extracted by projecting the knuckle print image onto a shift-and-difference matrix. Such a matrix enables directional image shifting and subtraction within a single matrix multiplication. The resultant difference image then goes through a sigmoidal activation for contrast enhancement. Subsequently, the Fourier spectrum of the contrast enhanced image is adopted as the holistic features of the given finger-knuckle-print image. The entire process of extracting the proposed features is expressed in an analytic form to facilitate a fast vectorized implementation. For cognition performance enhancement, the two directional line features are subsequently fused at the score level by minimizing the error counts of the extreme learning machine kernel. Extensive experiments are performed to compare the proposed method with competing methods using three public finger-knuckle-print databases. Our experimental results show encouraging performance in terms of verification accuracy and computational efficiency.
first_indexed 2024-10-01T04:54:45Z
format Journal Article
id ntu-10356/150715
institution Nanyang Technological University
language English
last_indexed 2024-10-01T04:54:45Z
publishDate 2021
record_format dspace
spelling ntu-10356/1507152021-06-02T02:16:25Z A line feature extraction method for finger-knuckle-print verification Kim, Jooyoung Oh, Kangrok Oh, Beom-Seok Lin, Zhiping Toh, Kar-Ann School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Finger-knuckle-print Verification Holistic Line Features Due to its mobility and reliability, the outer finger-knuckle-print (FKP) possesses several advantages over other biometric traits of the hand. However, most existing state-of-the-art methods utilize either local features alone or together with global features for FKP verification. These methods often demand high computational cost despite their high verification accuracy. In this paper, we propose a novel and fast matrix projection method for extracting line features from the finger-knuckle-print for person verification. Essentially, both the horizontal and the vertical knuckle lines are extracted by projecting the knuckle print image onto a shift-and-difference matrix. Such a matrix enables directional image shifting and subtraction within a single matrix multiplication. The resultant difference image then goes through a sigmoidal activation for contrast enhancement. Subsequently, the Fourier spectrum of the contrast enhanced image is adopted as the holistic features of the given finger-knuckle-print image. The entire process of extracting the proposed features is expressed in an analytic form to facilitate a fast vectorized implementation. For cognition performance enhancement, the two directional line features are subsequently fused at the score level by minimizing the error counts of the extreme learning machine kernel. Extensive experiments are performed to compare the proposed method with competing methods using three public finger-knuckle-print databases. Our experimental results show encouraging performance in terms of verification accuracy and computational efficiency. This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology (Grant number: NRF-2015R1D1A1A09061316). 2021-06-02T02:16:25Z 2021-06-02T02:16:25Z 2019 Journal Article Kim, J., Oh, K., Oh, B., Lin, Z. & Toh, K. (2019). A line feature extraction method for finger-knuckle-print verification. Cognitive Computation, 11(1), 50-70. https://dx.doi.org/10.1007/s12559-018-9593-6 1866-9956 0000-0002-3736-003X https://hdl.handle.net/10356/150715 10.1007/s12559-018-9593-6 2-s2.0-85053706342 1 11 50 70 en Cognitive Computation © 2018 Springer Science Business Media, LLC, part of Springer Nature. All rights reserved.
spellingShingle Engineering::Electrical and electronic engineering
Finger-knuckle-print Verification
Holistic Line Features
Kim, Jooyoung
Oh, Kangrok
Oh, Beom-Seok
Lin, Zhiping
Toh, Kar-Ann
A line feature extraction method for finger-knuckle-print verification
title A line feature extraction method for finger-knuckle-print verification
title_full A line feature extraction method for finger-knuckle-print verification
title_fullStr A line feature extraction method for finger-knuckle-print verification
title_full_unstemmed A line feature extraction method for finger-knuckle-print verification
title_short A line feature extraction method for finger-knuckle-print verification
title_sort line feature extraction method for finger knuckle print verification
topic Engineering::Electrical and electronic engineering
Finger-knuckle-print Verification
Holistic Line Features
url https://hdl.handle.net/10356/150715
work_keys_str_mv AT kimjooyoung alinefeatureextractionmethodforfingerknuckleprintverification
AT ohkangrok alinefeatureextractionmethodforfingerknuckleprintverification
AT ohbeomseok alinefeatureextractionmethodforfingerknuckleprintverification
AT linzhiping alinefeatureextractionmethodforfingerknuckleprintverification
AT tohkarann alinefeatureextractionmethodforfingerknuckleprintverification
AT kimjooyoung linefeatureextractionmethodforfingerknuckleprintverification
AT ohkangrok linefeatureextractionmethodforfingerknuckleprintverification
AT ohbeomseok linefeatureextractionmethodforfingerknuckleprintverification
AT linzhiping linefeatureextractionmethodforfingerknuckleprintverification
AT tohkarann linefeatureextractionmethodforfingerknuckleprintverification