Palmprint authentication using pattern classification techniques

Authors:
Amioy Kumar;Mayank Bhargava;Rohan Gupta;Bijaya Ketan Panigrahi
Affiliations:
Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi, India;Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi, India;Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi, India;Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi, India
Venue:
SEMCCO'11 Proceedings of the Second international conference on Swarm, Evolutionary, and Memetic Computing - Volume Part I
Year:
2011

Citing 7
Cited 0

Probabilistic neural networks

Neural Networks
High Confidence Visual Recognition of Persons by a Test of Statistical Independence

IEEE Transactions on Pattern Analysis and Machine Intelligence
Palmprint recognition using eigenpalms features

Pattern Recognition Letters
Online Palmprint Identification

IEEE Transactions on Pattern Analysis and Machine Intelligence
IKNN: Informative K-Nearest Neighbor Pattern Classification

PKDD 2007 Proceedings of the 11th European conference on Principles and Practice of Knowledge Discovery in Databases
A survey of palmprint recognition

Pattern Recognition
Personal authentication using multiple palmprint representation

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Biometric technology incorporates several physiological and behavioral traits for personal authentication whenever deployed for security systems. Palmprint is one of the physiological trait has been utilized several times for key applications. This paper proposes a pattern classification approach for palm print authentication which utilizes soft computing techniques to classify a claimed identity into its appropriate class. The presented approach operates on feature level classification using 2D Gabor filter for feature representation and Principal Component Analysis (PCA) for computing weights as features .These features are used to train the classifiers by taking each user as a separate class. K-Nearest Neighbor, (KNN) and Probabilistic Neural Network (PNN) based classifiers are utilized in classification. These classifiers are also employed for score level classification by computing the matching scores using normalized hamming distance. The experiments are carried out on HongKong PolyU database which has been a benchmark database for palmprint authentication. The proposed techniques operate on very low false acceptance rate (FAR) of .0011% and false rejection rate (FRR) of 3% which shows the reliability of the proposed work.