Novel Local Coding Algorithm for Finger Multimodal Feature Description and Recognition
Recently, finger-based biometrics, including fingerprint (FP), finger-vein (FV) and finger-knuckle-print (FKP) with high convenience and user friendliness, have attracted much attention for personal identification. The features expression which is insensitive to illumination and pose variation are b...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-05-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/9/2213 |
id |
doaj-620a4995734c4f768854b467b2f94f2d |
---|---|
record_format |
Article |
spelling |
doaj-620a4995734c4f768854b467b2f94f2d2020-11-24T21:28:00ZengMDPI AGSensors1424-82202019-05-01199221310.3390/s19092213s19092213Novel Local Coding Algorithm for Finger Multimodal Feature Description and RecognitionShuyi Li0Haigang Zhang1Yihua Shi2Jinfeng Yang3Tianjin Key Laboratory for Advanced Signal Processing, Civil Aviation University of China, Tianjin 300300, ChinaTianjin Key Laboratory for Advanced Signal Processing, Civil Aviation University of China, Tianjin 300300, ChinaShenzhen Polytechnic, Shenzhen 518055, ChinaShenzhen Polytechnic, Shenzhen 518055, ChinaRecently, finger-based biometrics, including fingerprint (FP), finger-vein (FV) and finger-knuckle-print (FKP) with high convenience and user friendliness, have attracted much attention for personal identification. The features expression which is insensitive to illumination and pose variation are beneficial for finger trimodal recognition performance improvement. Therefore, exploring suitable method of reliable feature description is of great significance for developing finger-based biometric recognition system. In this paper, we first propose a correction approach for dealing with the pose inconsistency among the finger trimodal images, and then introduce a novel local coding-based feature expression method to further implement feature fusion of FP, FV, and FKP traits. First, for the coding scheme a bank of oriented Gabor filters is used for direction feature enhancement in finger images. Then, a generalized symmetric local graph structure (GSLGS) is developed to fully express the position and orientation relationships among neighborhood pixels. Experimental results on our own-built finger trimodal database show that the proposed coding-based approach achieves excellent performance in improving the matching accuracy and recognition efficiency.https://www.mdpi.com/1424-8220/19/9/2213finger featuresmultimodal recognitionlocal codingGabor filterLGS |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Shuyi Li Haigang Zhang Yihua Shi Jinfeng Yang |
spellingShingle |
Shuyi Li Haigang Zhang Yihua Shi Jinfeng Yang Novel Local Coding Algorithm for Finger Multimodal Feature Description and Recognition Sensors finger features multimodal recognition local coding Gabor filter LGS |
author_facet |
Shuyi Li Haigang Zhang Yihua Shi Jinfeng Yang |
author_sort |
Shuyi Li |
title |
Novel Local Coding Algorithm for Finger Multimodal Feature Description and Recognition |
title_short |
Novel Local Coding Algorithm for Finger Multimodal Feature Description and Recognition |
title_full |
Novel Local Coding Algorithm for Finger Multimodal Feature Description and Recognition |
title_fullStr |
Novel Local Coding Algorithm for Finger Multimodal Feature Description and Recognition |
title_full_unstemmed |
Novel Local Coding Algorithm for Finger Multimodal Feature Description and Recognition |
title_sort |
novel local coding algorithm for finger multimodal feature description and recognition |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2019-05-01 |
description |
Recently, finger-based biometrics, including fingerprint (FP), finger-vein (FV) and finger-knuckle-print (FKP) with high convenience and user friendliness, have attracted much attention for personal identification. The features expression which is insensitive to illumination and pose variation are beneficial for finger trimodal recognition performance improvement. Therefore, exploring suitable method of reliable feature description is of great significance for developing finger-based biometric recognition system. In this paper, we first propose a correction approach for dealing with the pose inconsistency among the finger trimodal images, and then introduce a novel local coding-based feature expression method to further implement feature fusion of FP, FV, and FKP traits. First, for the coding scheme a bank of oriented Gabor filters is used for direction feature enhancement in finger images. Then, a generalized symmetric local graph structure (GSLGS) is developed to fully express the position and orientation relationships among neighborhood pixels. Experimental results on our own-built finger trimodal database show that the proposed coding-based approach achieves excellent performance in improving the matching accuracy and recognition efficiency. |
topic |
finger features multimodal recognition local coding Gabor filter LGS |
url |
https://www.mdpi.com/1424-8220/19/9/2213 |
work_keys_str_mv |
AT shuyili novellocalcodingalgorithmforfingermultimodalfeaturedescriptionandrecognition AT haigangzhang novellocalcodingalgorithmforfingermultimodalfeaturedescriptionandrecognition AT yihuashi novellocalcodingalgorithmforfingermultimodalfeaturedescriptionandrecognition AT jinfengyang novellocalcodingalgorithmforfingermultimodalfeaturedescriptionandrecognition |
_version_ |
1725972098904489984 |