A New Filter Generation Method in PCANet for Finger Vein Recognition
Currently, the used of deep learning method has attracted widespread attention in machine learning, especially in Biometric. Many deep learning methods have been proposed like convolutional neural network (CNN), AlexNet and principal component analysis network (PCANet). Among the methods employed, P...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8842572/ |
| _version_ | 1818947684350820352 |
|---|---|
| author | Nurul Maisarah Kamaruddin Bakhtiar Affendi Rosdi |
| author_facet | Nurul Maisarah Kamaruddin Bakhtiar Affendi Rosdi |
| author_sort | Nurul Maisarah Kamaruddin |
| collection | DOAJ |
| description | Currently, the used of deep learning method has attracted widespread attention in machine learning, especially in Biometric. Many deep learning methods have been proposed like convolutional neural network (CNN), AlexNet and principal component analysis network (PCANet). Among the methods employed, PCANet is believed to be the most effective method because of its promising performance in biometric. However, the current filter generation approach in PCANet does not consider the characteristics of the image, such as vein lines for finger vein recognition. To address this limitation, we proposed a new filter generation method that can consider the essential features of the image, such as the use of vein lines for finger vein recognition. The filter of the proposed method was generated by finding the correlation between two view images, which was original grayscale image and vein line image using canonical correlation analysis (CCA) method. Then, we evaluated this proposed method with the three public finger vein image database, FV-USM, SDUMLA-HMT and THU-FVT2. The results showed that the proposed method produced higher accuracy compared to other state-of-the-art features of finger vein recognition biometric method. |
| first_indexed | 2024-12-20T08:34:49Z |
| format | Article |
| id | doaj.art-e5fdd5b12f954f89bde95de2013393cf |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T08:34:49Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-e5fdd5b12f954f89bde95de2013393cf2022-12-21T19:46:36ZengIEEEIEEE Access2169-35362019-01-01713296613297810.1109/ACCESS.2019.29415558842572A New Filter Generation Method in PCANet for Finger Vein RecognitionNurul Maisarah Kamaruddin0https://orcid.org/0000-0002-1998-5992Bakhtiar Affendi Rosdi1https://orcid.org/0000-0002-0917-3886Intelligent Biometric Group, School of Electrical and Electronic Engineering, Universiti Sains Malaysia, Engineering Campus, Pulau Pinang, MalaysiaIntelligent Biometric Group, School of Electrical and Electronic Engineering, Universiti Sains Malaysia, Engineering Campus, Pulau Pinang, MalaysiaCurrently, the used of deep learning method has attracted widespread attention in machine learning, especially in Biometric. Many deep learning methods have been proposed like convolutional neural network (CNN), AlexNet and principal component analysis network (PCANet). Among the methods employed, PCANet is believed to be the most effective method because of its promising performance in biometric. However, the current filter generation approach in PCANet does not consider the characteristics of the image, such as vein lines for finger vein recognition. To address this limitation, we proposed a new filter generation method that can consider the essential features of the image, such as the use of vein lines for finger vein recognition. The filter of the proposed method was generated by finding the correlation between two view images, which was original grayscale image and vein line image using canonical correlation analysis (CCA) method. Then, we evaluated this proposed method with the three public finger vein image database, FV-USM, SDUMLA-HMT and THU-FVT2. The results showed that the proposed method produced higher accuracy compared to other state-of-the-art features of finger vein recognition biometric method.https://ieeexplore.ieee.org/document/8842572/Deep learningfinger vein based biometriccanonical correlation analysisprincipal component analysisPCANetfinger vein recognition |
| spellingShingle | Nurul Maisarah Kamaruddin Bakhtiar Affendi Rosdi A New Filter Generation Method in PCANet for Finger Vein Recognition IEEE Access Deep learning finger vein based biometric canonical correlation analysis principal component analysis PCANet finger vein recognition |
| title | A New Filter Generation Method in PCANet for Finger Vein Recognition |
| title_full | A New Filter Generation Method in PCANet for Finger Vein Recognition |
| title_fullStr | A New Filter Generation Method in PCANet for Finger Vein Recognition |
| title_full_unstemmed | A New Filter Generation Method in PCANet for Finger Vein Recognition |
| title_short | A New Filter Generation Method in PCANet for Finger Vein Recognition |
| title_sort | new filter generation method in pcanet for finger vein recognition |
| topic | Deep learning finger vein based biometric canonical correlation analysis principal component analysis PCANet finger vein recognition |
| url | https://ieeexplore.ieee.org/document/8842572/ |
| work_keys_str_mv | AT nurulmaisarahkamaruddin anewfiltergenerationmethodinpcanetforfingerveinrecognition AT bakhtiaraffendirosdi anewfiltergenerationmethodinpcanetforfingerveinrecognition AT nurulmaisarahkamaruddin newfiltergenerationmethodinpcanetforfingerveinrecognition AT bakhtiaraffendirosdi newfiltergenerationmethodinpcanetforfingerveinrecognition |