Performance Analysis of Feature Extraction and its Fusion Techniques for Iris Recognition System

Performance Analysis of Feature Extraction and its Fusion Techniques for Iris Recognition System

Author by Aiyeniko, O

Journal/Publisher: Global Journal Of Artificial Intelligence

Volume/Edition: 2

Language: English

Pages: 1 - 12

Abstract

The extraction of feature shows a significant part of iris recogni-tion system. The robustness of recognition accuracy mostly de-pends on efficient extraction of feature. In the development of an effective recognition system, it is required that the best discrimi-nating feature available in an iris pattern to be properly extracted. This paper applied some selected feature extraction techniques: 1D Log-Gabor Filter (1D LGF), 2-D Gabor-Filter (2D GF), Dis-crete Cosine Tansform (DCT) and Scale Invariant Feature Trans-form (SIFT) for extraction of iris features and fusion technique. The CASIA iris image dataset was used to evaluate with evalua-tion parameters: False Acceptance Rate (FAR), False Rejection Rate (FRR), Error Rate (RA) and Recognition Accuracy (RA). The combined 1D Log-Gabor and 2D Gabor filter approach out-performed other techniques with 92.22% of recognition accura-cy, FRR of 0.0186, FAR of 0.1052 and ER of 2.87%.

Keywords


Other Co-Authors