Napredna pretraga

Pregled bibliografske jedinice broj: 388863

Finger-Based Personal Authentication: a Comparison of Feature-Extraction Methods Based on Principal Component Analysis, Most Discriminant Features and Regularised-Direct Linear Discriminant Analysis


Pavešić, Nikola; Ribarić, Slobodan; Grad, Benjamin
Finger-Based Personal Authentication: a Comparison of Feature-Extraction Methods Based on Principal Component Analysis, Most Discriminant Features and Regularised-Direct Linear Discriminant Analysis // IET Signal Processing, 3 (2009), 4; 269-281 (međunarodna recenzija, članak, znanstveni)


Naslov
Finger-Based Personal Authentication: a Comparison of Feature-Extraction Methods Based on Principal Component Analysis, Most Discriminant Features and Regularised-Direct Linear Discriminant Analysis

Autori
Pavešić, Nikola ; Ribarić, Slobodan ; Grad, Benjamin

Izvornik
IET Signal Processing (1751-9675) 3 (2009), 4; 269-281

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Biometrics; LDA; MDF; RD-LDA; Feature Extraction; Authentication; Finger

Sažetak
In this paper, feature-extraction methods based on Principal Component Analysis (PCA), Most Discriminant Features (MDF), and Regularized-Direct Linear Discriminant Analysis (RD-LDA) are tested and compared in an experimental fingerbased personal authentication system. The system is multimodal and based on features extracted from eight regions of the hand: four fingerprints (the prints of the finger tips) and four digitprints (the prints of the fingers between the first and third phalanges). All of the regions are extracted from one-shot grey-level images of the palmar surface of four fingers of the right hand. The identification and verification experiments were conducted on a database consisting of 1840 finger images (184 people). The experiments showed that the best results were obtained with the RDLDA- based feature-extraction method − 99.98% correct identification for 920 tests and an Equal Error Rate (EER) of 0.01% for 64170 verification tests.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo



POVEZANOST RADA


Projekt / tema
036-0361935-1954 - Teorija, modeliranje i uporaba autonomno orijentiranih računarskih struktura (Slobodan Ribarić, )

Ustanove
Fakultet elektrotehnike i računarstva, Zagreb

Autor s matičnim brojem:
Slobodan Ribarić, (112300)

Citiraj ovu publikaciju

Pavešić, Nikola; Ribarić, Slobodan; Grad, Benjamin
Finger-Based Personal Authentication: a Comparison of Feature-Extraction Methods Based on Principal Component Analysis, Most Discriminant Features and Regularised-Direct Linear Discriminant Analysis // IET Signal Processing, 3 (2009), 4; 269-281 (međunarodna recenzija, članak, znanstveni)
Pavešić, N., Ribarić, S. & Grad, B. (2009) Finger-Based Personal Authentication: a Comparison of Feature-Extraction Methods Based on Principal Component Analysis, Most Discriminant Features and Regularised-Direct Linear Discriminant Analysis. IET Signal Processing, 3 (4), 269-281.
@article{article, year = {2009}, pages = {269-281}, keywords = {Biometrics, LDA, MDF, RD-LDA, Feature Extraction, Authentication, Finger}, journal = {IET Signal Processing}, volume = {3}, number = {4}, issn = {1751-9675}, title = {Finger-Based Personal Authentication: a Comparison of Feature-Extraction Methods Based on Principal Component Analysis, Most Discriminant Features and Regularised-Direct Linear Discriminant Analysis}, keyword = {Biometrics, LDA, MDF, RD-LDA, Feature Extraction, Authentication, Finger} }

Časopis indeksira:


  • Current Contents Connect (CCC)
  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus