CONVOLUTIONAL NEURAL NETWORK ALGORITHM FOR CANCELLABLE FACE TEMPLATE

Biometrics systems utilizing hand geometry, fingerprint, iris, face, palm print, voice, gesture, and palm print have been utilised for authentication purposes. Through these templates, the face template is suggested as the strongest. However, problems still exist in face-matching implementation whic...

Full description

Saved in:
Bibliographic Details
Published inScientific Bulletin. Series C, Electrical Engineering and Computer Science no. 1; p. 155
Main Authors Alwan, Hiba Basim, Ku-Mahamud, Ku Ruhana
Format Journal Article
LanguageEnglish
Published Bucharest University Polytechnica of Bucharest 01.01.2024
Subjects
Algorithms
Artificial neural networks
Biometrics
Datasets
Error analysis
Feature extraction
Matching
Neural networks
Palm
Security
Online AccessGet full text

Cover

More Information
Summary:Biometrics systems utilizing hand geometry, fingerprint, iris, face, palm print, voice, gesture, and palm print have been utilised for authentication purposes. Through these templates, the face template is suggested as the strongest. However, problems still exist in face-matching implementation which affects biometric security. Thus, in this paper, a new cancellable face image algorithm using the Convolution Neural Network (CNN) feature extraction technique and Winner-Takes-All hashing method is proposed. The algorithm is to overcome the problem of matching which will enhance its security. ORL and Yale datasets were utilized in the evaluation of the proposed algorithm. Several common algorithms were utilised in the comparison based on Equal Error Ratio (ERR) measurement. The outcomes displayed the verification performance of the unimportant differences with EER = 0.95% and 3.25% for the extended version of the face dataset for the Yale and ORL face datasets, respectively. The acceptable implementation of the proposed algorithm demonstrates that it can be used for the security purpose of biometric trait tasks.
ISSN:2286-3540