Iris Verification Using Optimized SVM, Ensemble, KNN, and NN Feature Classifiers on Selected DWT and Gabor Features Using mRMR, x2, ANOVA and Kruskal-Wallis Ranking Techniques

International Journal of Electronics and Communication Engineering

© 2025 by SSRG - IJECE Journal

Volume 12 Issue 11

Year of Publication : 2025

Authors : Sayan Das, Biswajit Kar

10.14445/23488549/IJECE-V12I11P113

How to Cite?

Sayan Das, Biswajit Kar, "Iris Verification Using Optimized SVM, Ensemble, KNN, and NN Feature Classifiers on Selected DWT and Gabor Features Using mRMR, x2, ANOVA and Kruskal-Wallis Ranking Techniques," SSRG International Journal of Electronics and Communication Engineering, vol. 12,  no. 11, pp. 155-165, 2025. Crossref, https://doi.org/10.14445/23488549/IJECE-V12I11P113

Abstract:

The iris verification is now one of the accurate biometric verification methods because of the uniqueness of the iris structure and durable patterns of the iris. It stays consistent over time. Several distinct features can be extracted from the iris crypt and furrow patterns. In this study, iris features extracted using DWT and Gabor kernels are combined. Four feature ranking techniques are used to select the most relevant features, including Chi-square (x2), Minimum Redundancy Maximum Relevance (mRMR), Kruskal-Wallis tests, and Analysis of Variance (ANOVA). The top-ranked features are identified as the global features. Using them, the verification accuracy was evaluated using Discriminant Analysis, k-Nearest Neighbours (KNN), Ensemble Methods, Naive Bayes Classifiers, Support Vector Machines (SVM), and Neural Networks (NN) separately. The SVM, Ensemble, KNN, and NN models were then optimized through a hyperparameter-tuned Bayesian optimizer. A comparison of the verification performance of these machine learning methods was studied. It is found that the experimental results show excellent verification accuracies for the optimized classification models: SVM (94.1%), KNN (93.9%), Ensemble Methods (85.6%), and Neural Networks (88.3%). These findings highlight the importance of feature selection and model optimization in improving the classification models, such as SVM, Ensemble, KNN, and NN, for iris verification. The optimized SVM achieved the highest verification accuracy on the UBIRIS iris database. This result surpasses some previous studies. So, this research provides valuable insights that improve the accuracy and efficiency of an iris verification system.

Keywords:

Bayesian optimization, DWT, Gabor, Feature ranking, Iris.

References:

[1] Kiran B. Raja, R. Raghavendra, and Christoph Busch, “Video Presentation Attack Detection in Visible Spectrum Iris Recognition Using Magnified Phase Information,” IEEE Transactions on Information Forensics and Security, vol. 10, no. 10, pp. 2048-2056, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Hicham Ohmaid et al., “Comparison between SVM and KNN Classifiers for Iris Recognition using a New Unsupervised Neural Approach in Segmentation,” IAES International Journal of Artificial Intelligence, vol. 9, no. 3, pp. 429-438, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Sandipan P Narote et al., “An Iris Recognition based on Dual Tree Complex Wavelet Transform,” TENCON 2007 - 2007 IEEE Region 10 Conference, Taipei, Taiwan, pp. 1-4, 2007.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Suchitra Khoje, and Sanjay Mohite, “A SVM Based Iris Recognition using Wavelet Packet Transform and Manhattan Distance,” International Journal of Scientific and Technology Research, vol. 9, no. 2, pp. 6232-6236, 2020.
[Google Scholar] [Publisher Link]
[5] Ernest Yeboah Boateng, Joseph Otoo, and Daniel A. Abaye, “Basic Tenets of Classification Algorithms K-Nearest-Neighbor, Support Vector Machine, Random Forest and Neural Network: A Review,” Journal of Data Analysis and Information Processing, vol. 8, no. 4, pp. 341-357, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Ahmed AK. Tahir, and Steluta Anghelus, “Improving Iris Recognition Accuracy Using Gabor Kernels With Near-Horizontal Orientations,” International Journal of Advances in Signal and Image Sciences, vol. 8, no. 1, pp. 25-39, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Ajay Kumar, and Arun Passi, “Comparison and Combination of Iris Matchers for Reliable Personal Authentication,” Pattern Recognition, vol. 43, no. 3, pp. 1016-1026, 2010.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Tapas Bhadra et al., “Comparison of Five Supervised Feature Selection Algorithms Leading to Top Features and Gene Signatures from Multi-Omics Data in Cancer,” BMC Bioinformatics, vol. 23, pp. 1-18, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Dwi Andini Putri et al., “Comparison of Naive Bayes Algorithm and Support Vector Machine using PSO Feature Selection for Sentiment Analysis on E-Wallet Review,” Journal of Physics: Conference Series, vol. 1641, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Yiyan Zhang et al., “Empirical Study of Seven Data Mining Algorithms on Different Characteristics of Datasets for Biomedical Classification Applications,” Biomedical Engineering Online, vol. 16, pp. 1-15, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Maryim Omran, and Ebtesam N. AlShemmary, “An Iris Recognition System Using Deep convolutional Neural Network,” Journal of Physics: Conference Series, vol. 1530, pp. 1-12, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Hunny Mehrotra et al., “An Efficient Iris Recognition using Local Feature Descriptor,” 2009 16th IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, pp. 1957-1960, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Hosam El-Sofany, Belgacem Bouallegue, and Yasser M. Abd El-Latif, “A Proposed Biometric Authentication Hybrid Approach using Iris Recognition for Improving Cloud Security,” Heliyon, vol. 10, pp. 1-16, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[14] H. Chen, and B.R. Bakshi, “Linear Approaches for Nonlinear Modeling,” Comprehensive Chemometrics, vol. 3, pp. 453-462, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Bashra Kadhim Oleiwi Chabor Alwawi, and Ali Fadhil Yaseen Althabhawee, “Towards More Accurate and Efficient Human Iris Recognition Model using Deep Learning Technology,” Telkomnika (Telecommunication Computing Electronics and Control), vol. 20, no. 4, pp. 817-824, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Yimin Yin et al., “Deep Learning for Iris Recognition: A Review,” Neural Computing and Applications, vol. 37, pp. 11125-11173, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Luiz A. Zanlorensi et al., “The Impact of Preprocessing on Deep Representations for Iris Recognition on Unconstrained Environments,” 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), Parana, Brazil, pp. 289-296, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Amer Sallam et al., “Iris Recognition System Using Convolutional Neural Network,” 2021 International Conference on Software Engineering & Computer Systems and 4th International Conference on Computational Science and Information Management (ICSECS-ICOCSIM), Pekan, Malaysia, pp. 109-114, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Shervin Minaee, Amirali Abdolrashidiy, and Yao Wang, “An Experimental Study of Deep Convolutional Features For Iris Recognition,” 2016 IEEE Signal Processing in Medicine and Biology Symposium (SPMB), Philadelphia, PA, USA, pp. 1-6, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Yuqing He, Yangsheng Wang, and Tieniu Tan, “Iris Image Capture System Design for Personal Identification,” Advances in Biometric Person Authentication, vol. 3338, pp. 539-545, 2004.
[CrossRef] [Google Scholar] [Publisher Link]
[21] J. Daugman, “How Iris Recognition Works,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 14, no. 1, pp. 21-30, 2004.
[CrossRef] [Google Scholar] [Publisher Link]
[22] John Daugman, “New Methods in Iris Recognition,” IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, vol. 37, no. 5, pp. 1167-1175, 2007.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Anil K. Jain et al., Handbook of Biometrics, Springer US, pp. 1-556, 2008.
[Google Scholar] [Publisher Link]
[24] P. White, “Transforms, Wavelets,” Encyclopedia of Vibration, pp. 1419-1435, 2001.
[CrossRef] [Publisher Link]
[25] John Daugman, “Iris Encoding and Recognition using Gabor Wavelets,” Encyclopedia of Biometrics, pp. 787-797, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Hanchuan Peng, Fuhui Long, and C. Ding, “Feature Selection Based on Mutual Information: Criteria of Max-Dependency, Max-Relevance, and Min-Redundancy,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 8, pp. 1226-1238, 2005.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Alisha Sikri, N.P. Singh, and Surjeet Dalal, “Chi-Square Method of Feature Selection: Impact of Pre-Processing of Data,” International Journal of Intelligent Systems and applications in Engineering, vol. 11, no. 3s, pp. 1-8, 2023.
[Google Scholar] [Publisher Link]
[28] M.O. Arowolo et al., “A Feature Selection Based on One Way Anova For Microarray Data Classification,” Al-Hikmah Journal of Pure & Applied Sciences, vol. 3, pp. 30-35, 2016.
[Google Scholar] [Publisher Link]
[29] William H. Kruskal, and W. Allen Wallis, “Use of Ranks in One-Criterion Variance Analysis,” Journal of the American Statistical Association, vol. 47, no. 260, pp. 583-621, 1952.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Hugo Proença, and Luís A. Alexandre, “UBIRIS: A Noisy Iris Image Database,” 13th International Conference on Image Analysis and Processing - ICIAP 2005, Cagliari, Italy, pp. 970-977, 2025.
[CrossRef] [Google Scholar] [Publisher Link]