Scinovex
article

Efficient Iris Recognition by Fusion of Matching Scores obtained by Lifting DWT and Log-Gabor methods of Feature Extraction

International journal of applied research · 2015 · Vol. 1(9) · pp. 1067–1073

Abstract

Iris Recognition technology is gaining wide range of applications day by day because of its accuracy and reliability. The main reason for this is the varying iris texture of every individual. However, iris images are usually distorted by various sources of noise such as occlusions by eyelashes and eyelids, error during iris localization, iris deformation. etc. Therefore, development of accurate iris recognition techniques which can be more tolerant to noise is highly desirable. In this paper, an efficient algorithm is proposed to increase the accuracy of Iris recognition which is more than that of existing methods of iris recognition. In addition, since two methods of feature extraction i.e. Lifting DWT and Log Gabor have been used and also the matching scores i.e. TSR (Total Successive Rate) of these two methods are fused in the proposed algorithm, the experimental results shows that the iris recognition rate will be more accurate compared to other Iris Recognition system. rnGeneral TermsrnImage processing, Iris recognition, Lifting DWT, Log Gabor Filter.

Biometric Identification and SecurityFace and Expression RecognitionUser Authentication and Security SystemsIris recognitionArtificial intelligenceIRIS (biosensor)Pattern recognition (psychology)Computer scienceGabor filterComputer visionFeature extractionFeature (linguistics)Matching (statistics)
Citations
5
FWCI
1.16
field-weighted impact
References
12
Percentile
81%
vs. same field & year
Citations per year
References
On combining classifiers
IEEE Transactions on Pattern Analysis and Machine Intelligence · 1998 · 5,240 citations
Citation Network

How this paper connects to the literature. Drag to explore, click any node to open that paper.

Efficient Iris Recognition by Fusion of Matching Scores obtained by Lifting DWT and Log-Gabor methods of Feature Extraction · Scinovex