Authentication through gender classification from iris images using support vector machine

作     者：Khan, Amjad Rehman Doosti, Fatemeh Karimi, Mohsen Harouni, Majid Tariq, Usman Fati, Suliman Mohamed Ali Bahaj, Saeed 

作者机构：Prince Sultan Univ Artificial Intelligence & Data Analyt Lab CCIS Riyadh Saudi Arabia Asharfi Isfahani Univ Dept Comp Engn Esfahan Iran Islamic Azad Univ Dolatabad Branch Dept Comp Engn Esfahan Iran Prince Sattam bin Abdulaziz Univ Coll Comp Engn & Sci Alkharj Saudi Arabia Prince Sattam bin Abdulaziz Univ MIS Dept Coll Business Adm Alkharj Saudi Arabia 

出 版 物：《MICROSCOPY RESEARCH AND TECHNIQUE》 (显微镜研究与技术)

年 卷 期：2021年第84卷第11期

页      面：2666-2676页

核心收录：

学科分类：0710[理学-生物学] 1001[医学-基础医学(可授医学、理学学位)] 07[理学] 08[工学] 0804[工学-仪器科学与技术] 

主　　题：authentication digital security gender recognition iris image texture features oriented gradient histogram 

摘      要：Soft biometric information, such as gender, iris, and voice, can be helpful in various applications, such as security, authentication, and validation. Iris is secure biometrics with low forgery and error rates due to its highly certain features are being used in the last few decades. Iris recognition could be used both independently and in part for secure recognition and authentication systems. Existing iris-based gender classification techniques have low accuracy rates as well as high computational complexity. Accordingly, this paper presents an authentication approach through gender classification from iris images using support vector machine (SVM) that has an excellent response to sustained changes using the Zernike, Legendre invariant moments, and Gradient-oriented histogram. In this study, invariant moments are used as feature extraction from iris images. After extracting these descriptors attributes, the attributes are categorized through keycode fusion. SVM is employed for gender classification using a fused feature vector. The proposed approach is evaluated on the CVBL data set and results are compared in state of the art based on local binary patterns and Gabor filters. The proposed approach came out with 98% gender classification rate with low computational complexity that could be used as an authentication measure.