A New Approach for Iris and Fingerprint Recognition based on KPCA and LLE Algorithm

Author(s):

Midun Thangavel , Nehru Institute of Technology, India; Dr. Gandhimathi Amirthalingam, King Khalid University

Keywords:

KPCA, LLE, Iris, Fingerprint, Biometric

Abstract:

The paper presents the fusion of two biometric iris and fingerprint to improve the recognition rate. A solution based on Kernel Principal Component Analysis (KPCA) and Locally Linear Embedding (LLE) algorithms are proposed for the iris and fingerprint recognition respectively. The KPCA is one of the most successful techniques that have been used to recognize iris. A non-linear algorithm called Locally Linear Embedding belonging to manifold learning technique is introduced and applied to recognize fingerprint. LLE is considered an effective algorithm for dimensional reduction. LLE preserves intrinsic structure and relationships in a high dimensional space when data are mapped into low dimensional space. The proposed system shows that multimodal recognition system is very efficient to reduce the false rejection rate (FRR) and false acceptance rate (FAR).

Other Details:

Manuscript Id	:	IJSTEV4I10083
Published in	:	Volume : 4, Issue : 10
Publication Date	:	01/05/2018
Page(s)	:	213-217

Download Article