Genetic Algorithm Based Feature Selection Level Fusion Using Fingerprint and Iris Biometrics

Abstract

An accuracy level of unimodal biometric recognition system is not very high because of noisy data, limited degrees of freedom, spoof attacks etc. problems. A multimodal biometric system which uses two or more biometric traits of an individual can overcome such problems. We propose a multimodal biometric recognition system that fuses the fingerprint and iris features at the feature extraction level. A feed-forward artificial neural networks (ANNs) model is used for recognition of a person. There is a need to make the training time shorter, so the feature selection level should be performed. A genetic algorithms (GAs) approach is used for feature selection of a combined data. As an experiment, the database of 60 users, 10 fingerprint images and 10 iris images taken from each person, is used. The test results are presented in the last stage of this research. Keywords: Multibiometric; feature selection; genetic algorithms; artificial neural networks. 585 Int. J. Patt. Recogn. Artif. Intell. 2008.22:585-600. Downloaded from www.worldscientific.com by UNIVERSITY OF SASKATCHEWAN on 02/03/15. For personal use only.

Designing efficient fusion schemes for multimodal biometric systems using face and palmprint

“…Finally, classification is carried out using a radial basis function (RBF) network. Interesting works on feature level fusion are reported in [19,3], where, some feature selection scheme is used to reduce the feature space. In [19], the feature level fusion of hand and face biometrics is carried out.…”

“…Furthermore, a feature selection scheme like SFFS is employed to select only dominant features from this fused feature space. In [3], a feature selection scheme based on genetic algorithm is employed to select the features from concatenated feature space of Iris and Fingerprint.…”

Rotated Wavelet Filters-Based Fingerprint Recognition

“…Srihari and Srinivasan 35 proposed the comparison of ROC and likelihood decision methods for automatic¯ngerprint veri¯cation. Altun et al 1 proposed genetic algorithm-based features for¯ngerprint matching. Bazen and Gerez 2 used thin plate spline model to describe nonlinear distortion between the minutiae points.…”

Efficient iris localisation using a guided filter

“…With advances in biometric technology, many biometric identification systems have been rapidly applied to various security applications and consumer electronic devices [1][2][3]. Iris recognition has a higher accuracy than other biometric recognitions such as face recognition, fingerprint recognition, vein recognition and speech recognition.…”