Home // ICCGI 2011, The Sixth International Multi-Conference on Computing in the Global Information Technology // View article

Logitboost-SO Learning Algorithm for Human Iris Recognition

Authors:
Wen-Shiung Chen
Lili Hsieh
Wei-Chih Tang

Keywords: Biometrics; Iris Recognition; Boosting; Adaboost; Logitboost.

Abstract:
Boosting has been used extensively in the field of machine learning. This work intends to apply boosting method to iris biometrics. The recognition performance of boosting-based classification can be improved greatly by means of different re-weighting rules and different voting regulations based on the assigned weights. This paper proposes a novel Logitboost-SO algorithm which integrates similarity-oriented concepts into additive logistic model. We modify the existing manner of combining classifiers with Logitboost by utilizing multi-weight update rule to refine boosting algorithm. The experi¬mental results show that Logitboost-SO applied to iris recognition is better than existing boosting algorithms.

Pages: 165 to 170

Copyright: Copyright (c) IARIA, 2011

Publication date: June 19, 2011

Published in: conference

ISSN: 2308-4529

ISBN: 978-1-61208-139-7

Location: Luxembourg City, Luxembourg

Dates: from June 19, 2011 to June 24, 2011