Implementing feature selection for multimodal biometrics
by K.S. Vairavel; S. Valarmathy
International Journal of Biomedical Engineering and Technology (IJBET), Vol. 23, No. 2/3/4, 2017

Abstract: Biometrics recognises a person through physiological/behavioural attributes like fingerprint, face, iris, retina or DNA. Biometrics relates to a human being's physiological/behavioural characteristics and ensures different techniques that capture an individual's identity. Multimodal biometric system combines two/more traits that are not copied, forgotten or stolen. Feature extraction extracts discriminant features from samples which are represented in a feature vector. Feature vector thus got is of high dimension resulting in computation complexity and affecting classifiers performance. To offset this, feature selection obtains an optimal features subset. A multimodal biometric framework based on fingerprint, iris and face is presented in this paper. In this work, features are extracted using Gabor filter, Local Tetra Pattern and feature selection is performed by Genetic Algorithm (GA), Particle Swarm Optimisation (PSO) and proposed Hybrid PSO (HPSO). The proposed hybrid PSO-GA is more flexible and robust and the hybrid strategy avoids premature convergence providing better exploration of the search process. Experimental results demonstrate the effectiveness of the proposed algorithm.

Online publication date: Sat, 04-Mar-2017

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Biomedical Engineering and Technology (IJBET):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com