Wavelet-based Feature Extraction Algorithm for an Iris Recognition System

Abstract

Abstract-The success of iris recognition depends mainly on two factors: image acquisition and an iris recognition algorithm. In this study, we present a system that considers both factors and focuses on the latter. The proposed algorithm aims to find out the most efficient wavelet family and its coefficients for encoding the iris template of the experiment samples. The algorithm implemented in software performs segmentation, normalization, feature encoding, data storage, and matching. By using the Haar and Biorthogonal wavelet families at various levels feature encoding is performed by decomposing the normalized iris image. The vertical coefficient is encoded into the iris template and is stored in the database. The performance of the system is evaluated by using the number of degrees of freedom, False Reject Rate (FRR), False Accept Rate (FAR), and Equal Error Rate (EER) and the metrics show that the proposed algorithm can be employed for an iris recognition system.

Enhanced Isocentric Segmentor and Wavelet Rectangular Coder to Iris Segmentation and Recognition

“…The isocentric approach [9] only works in segmentation phase; therefore we have not compared its performance because our method is proposed for a segmentation and recognition phase of operation. From the results shown in table 4, one can observe that [17] and our proposed one yield the best performances, followed by [18,19]. This is because that these methods very well describe the texture features of the iris.…”

“…In our experiment, we have taken 80% of dataset for training and remaining 20% for testing. The effectiveness of the proposed technique is demonstrated by performing a comparison between the matching result of the proposed method of EISOS+WRC and the conventional methods [17,18,19]. In this result part, we have the two phases such as segmentation phase and recognition phase.…”

“…When analyzing table 7, we understand our proposed approach achieves the maximum accuracy of 99.75% but in [17,18,19] it achieves the accuracy value of 94%, 93% and 93.6 % respectively, for CASIA dataset. In [13], we obtain the accuracy of 94% by varying the parameters [18] we obtain the accuracy of 93% on the CASIA database and [19] we obtain the accuracy of 93.6% for varying hamming distance. Also table 7, explains the FAR and FRR rate of three different dataset.…”

“…The methods proposed by isocentric approach [9], PBIM based approach [17] SURF based approach [18] and Haar wavelet based approach [19] are the best known among existing schemes for iris recognition. Furthermore, they characterize local details of the iris based on phase, texture analysis, and local sharp variation representation.…”

Evaluation of Iris Recognition System on Multiple Feature Extraction Algorithms and its Combinations

“…Haar functions have been used from 1910 when they were introduced by the Hungarian mathematician Alfred Haar [9]. Haar wavelet is discontinuous, and resembles a step function.…”