A new approach of iris detection and recognition.

Biswas, Rubel; Uddin, Jia; Hasan, Md. Junayed

Abstract

This paper proposes an IRIS recognition and detection model for measuring the e-security. This proposed model consists of the following blocks: Segmentation and normalization, feature encoding and feature extraction, and classification. In first phase, histogram equalization and canny edge detection is used for object detection. And then, Hough Transformation is utilized for detecting the center of the pupil of an IRIS. In second phase, Daugmen's Rubber Sheet model and Log Gabor filter is used for normalization and encoding and as a feature extraction method GNS (Global Neighborhood Structure) map is used, finally extracted feature of GNS is feed to the SVM (Support Vector Machine) for training and testing. For our tested dataset, experimental results demonstrate 92% accuracy in real portion and 86% accuracy in imaginary portion for both eyes. In addition, our proposed model outperforms than other two conventional methods exhibiting higher accuracy.

Citation

BISWAS, R., UDDIN, J. and HASAN, M.J. 2017. A new approach of iris detection and recognition. International journal of electrical and computer engineering (IJECE) [online], 7(5), pages 2530-2536. Available from: http://doi.org/10.11591/ijece.v7i5.pp2530-2536

• Journal Article Type: Article
• Acceptance Date: Sep 11, 2017
• Online Publication Date: Oct 31, 2017
• Publication Date: Oct 31, 2017
• Deposit Date: Oct 26, 2023
• Publicly Available Date: Feb 5, 2024
• Journal: International journal of electrical and computer engineering (IJECE)
• Print ISSN: 2088-8708
• Electronic ISSN: 2722-2578
• Publisher: Institute of Advanced Engineering and Science
• Peer Reviewed: Peer Reviewed
• Volume: 7
• Issue: 5
• Pages: 2530-2536
• DOI: https://doi.org/10.11591/ijece.v7i5.pp2530-2536
• Keywords: Daugman’s rubber sheet; DNS (dominant neighborhood structure); E-secuirity; GNS (global neighborhood structure); Iris recognition
• Public URL: https://rgu-repository.worktribe.com/output/2093172