A Fuzzy-based Two-stage Biometric Sample Quality Evaluation System
Tauheed Ahmed, Monalisa Sarma, Debasis Samanta
Abstract
Performance of biometric systems is highly dependent on the quality of the input samples captured by the sensing device. Although measures are taken for capturing high quality images, but the authentication system mandates the analysis of captured images for selection of precise data. The benefit of such an analysis are two-fold; it helps to identify the best sample, and is useful for improving the sensor design, user interface for sample collection and providing data interchange standards. In this work, we propose to analyse the quality of the sample data by using a two-stage fuzzy quality evaluation system. The proposed work has been demonstrated on the iris images using CASIA - 3.0 Interval, CASIA 4.0 Interval and IIT Delhi iris database. We evaluate the -quality of the images by classifying them into classes. The experimental results verify the efficacy of the proposed method.
BibTeX
@inproceedings{icassp2019_afuzzybasedtwost,
title = {A Fuzzy-based Two-stage Biometric Sample Quality Evaluation System},
author = {Tauheed Ahmed and Monalisa Sarma and Debasis Samanta},
booktitle = {ICASSP 2019},
year = {2019}
}