IRIS Recognition Based On LBP and Combined LVQ Classifier

Abstract

Iris recognition is considered as one of the best biometric methods used for human identification and verification, this is because of its unique features that differ from one person to another, and its importance in the security field. This paper proposes an algorithm for iris recognition and classification using a system based on Local Binary Pattern and histogram properties as a statistical approaches for feature extraction , and Combined Learning Vector Quantization Classifier as Neural Network approach for classification, in order to build a hybrid model depends on both features. The localization and segmentation techniques are presented using both Canny edge detection and Hough Circular Transform in order to isolate an iris from the whole eye image and for noise detection .Feature vectors results from LBP is applied to a Combined LVQ classifier with different classes to determine the minimum acceptable performance, and the result is based on majority voting among several LVQ classifier. Different iris datasets CASIA, MMU1, MMU2, and LEI with different extensions and size are presented. Since LBP is working on a grayscale level so colored iris images should be transformed into a grayscale level. The proposed system gives a high recognition rate 99.87 % on different iris datasets compared with other methods.

Pengenalan Iris Menggunakan Fitur Local Binary Pattern Dan RBF Classifier

“…Penelitian lain juga dilakukan oleh [4] dengan menggunakan ekstraksi fitur wavelet dan jaringan saraf tiruan Radial Basis Function (RBF) dengan hasil pengenalan iris mata menghasilkan akurasi pengenalan tertinggi sebesar 72,5%. Menurut penelitian yang telah dilakukan [5] tentang pengenalan iris menggunakan fitur LBP dan LVQ Classifier didapatkan tingkat identifikasi dengan hasil sebesar 99,87%. Metode LBP banyak digunakan sebagai ekstraksi fitur yang telah dilakukan seperti pada penelitian [6] [7] [8] [9].…”

Iris Image Recognition using Optimized Kohonen Self Organizing Neural Network

“…The real challenge in this method is to determine the value of K, because as the K increases the computation complexity of the algorithm also increases. A neural network approach using Learning Vector Quantization (LVQ) is propounded for classifying iris by authors in [12]. This method has the supremacy of statistical and neural network characteristics to build the recognition system.…”

Performance evaluation of feature selection methods for ANN based iris recognition

“…Both the probabilistic and non probabilistic distance measures such as Bayes, Euclidean, KNearest Neighbor were used in [15] to classify iris pattern. In [8], [16], a modified competitive learning neural network (LVQ) was adopted for classification. Neural network was used for iris pattern classification in [17] - [19].…”