Traditional feature extraction methods, such as Gabor filter and competitive coding, have been widely used in finger-knuckle-print (FKP) recognition. However, these methods focus on manually designed features which may not achieve satisfying results on FKP images. In order to solve this problem, a novel batch-normalized Convolutional Neural Network (CNN) architecture with data augmentation for FKP recognition is proposed. Firstly, a novel batch-normalized CNN is designed specifically for FKP recognition. Then, random histogram equalization is adopted as data augmentation here for training the CNN in FKP recognition. Meanwhile, batch-normalization is adopted to avoid overfitting during network training. Extensive experiments performed on the PolyU FKP database show that compared with traditional feature extraction method, the proposed method can not only extract more discriminative features, but also improve the accuracy of FKP recognition.
A Novel Finger-Knuckle-Print Recognition Based on Batch-Normalized CNN / Y. Zhai, H. Cao, L. Cao, H. Ma, J. Gan, J. Zeng, V. Piuri, F. Scotti, W. Deng, Y. Zhi, J. Wang (LECTURE NOTES IN COMPUTER SCIENCE). - In: Biometric Recognition / [a cura di] J. Zhou, Y. Wang, Z. Sun, Z. Jia, J. Feng, S. Shan, K. Ubul, Z. Guo. - [s.l] : Springer, 2018. - ISBN 9783319979083. - pp. 11-21 (( Intervento presentato al 13. convegno Chinese Conference on Biometric Recognition (CCBR) tenutosi a Urumqi nel 2018 [10.1007/978-3-319-97909-0_2].
A Novel Finger-Knuckle-Print Recognition Based on Batch-Normalized CNN
V. Piuri;F. Scotti;
2018
Abstract
Traditional feature extraction methods, such as Gabor filter and competitive coding, have been widely used in finger-knuckle-print (FKP) recognition. However, these methods focus on manually designed features which may not achieve satisfying results on FKP images. In order to solve this problem, a novel batch-normalized Convolutional Neural Network (CNN) architecture with data augmentation for FKP recognition is proposed. Firstly, a novel batch-normalized CNN is designed specifically for FKP recognition. Then, random histogram equalization is adopted as data augmentation here for training the CNN in FKP recognition. Meanwhile, batch-normalization is adopted to avoid overfitting during network training. Extensive experiments performed on the PolyU FKP database show that compared with traditional feature extraction method, the proposed method can not only extract more discriminative features, but also improve the accuracy of FKP recognition.File | Dimensione | Formato | |
---|---|---|---|
2018_Book_BiometricRecognition-pages-27-37.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
406.98 kB
Formato
Adobe PDF
|
406.98 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.