Low-quality fingerprint classification using deep neural network

Fingerprint recognition systems mainly use minutiae points information. As shown in many previous research works, fingerprint images do not always have good quality to be used by automatic fingerprint recognition systems. To tackle this challenge, in this work, the authors are focusing on very low-q...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IET biometrics Ročník 7; číslo 6; s. 550 - 556
Hlavní autori: Tertychnyi, Pavlo, Ozcinar, Cagri, Anbarjafari, Gholamreza
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Stevenage The Institution of Engineering and Technology 01.11.2018
John Wiley & Sons, Inc
Predmet:
Algorithms
Artificial neural networks
automatic fingerprint recognition systems
Biometric recognition systems
blurred fingerprint classes
Classification
Datasets
deep neural network algorithm
distortions
fingerprint identification
Fingerprint verification
Fourier transforms
high performance
Identification
image classification
Image quality
low quality fingerprint classification
low‐quality fingerprint database
low‐quality fingerprint images
minutiae points information
neural nets
Neural networks
robustness
Special Section: ‘Biometrics as-a-service’: thepath ahead?
Support vector machines
VGG16 based deep network
fingerprint identification
image classification
robustness
blurred fingerprint classes
automatic fingerprint recognition systems
low-quality fingerprint database
deep neural network algorithm
low quality fingerprint classification
low-quality fingerprint images
VGG16 based deep network
minutiae points information
high performance
distortions
neural nets
ISSN:2047-4938, 2047-4946, 2047-4946
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Fingerprint recognition systems mainly use minutiae points information. As shown in many previous research works, fingerprint images do not always have good quality to be used by automatic fingerprint recognition systems. To tackle this challenge, in this work, the authors are focusing on very low-quality fingerprint images, which contain several well-known distortions such as dryness, wetness, physical damage, presence of dots, and blurriness. They develop an efficient, with high accuracy, deep neural network algorithm, which recognises such low-quality fingerprints. The experimental results have been obtained from the real low-quality fingerprint database, and the achieved results show the high performance and robustness of the introduced deep network technique. The VGG16-based deep network achieves the highest performance of 93% for dry and the lowest performance of 84% for blurred fingerprint classes.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2047-4938
2047-4946
2047-4946
DOI:10.1049/iet-bmt.2018.5074