Synergistic Hybrid AI Framework for Optimized Iris Recognition: BWT-RBFNN-ICA (BRICA) Model
Abstract
This study details the Berkeley Wavelet Transform with Imperialist Competitive Radial Basis Network (BRICA) model, an advanced hybrid artificial intelligence framework designed for human iris recognition to achieve high accuracy and computational efficiency. The proposed architecture combines the Berkeley Wavelet Transform (BWT) for spatial-frequency feature extraction with a Radial Basis Function Neural Network (RBFNN) optimized by the Imperialist Competitive Algorithm (ICA) for pattern classification. Evaluated on benchmark iris datasets, this system achieves exceptional performance, reaching over accuracy on CASIA-Iris V3 and on the UCI dataset, alongside a low Equal Error Rate () and minimal computational overhead. The findings demonstrate that combining BWT multi-resolution extraction with ICA-driven neural network optimization provides a fast, highly accurate, and robust solution for real-world biometric applications.
Keywords
Full Text:
AbstractReferences
Sardar, M., S. Mitra, and B.U. Shankar, 'Iris localization using rough entropy and CSA: A soft computing approach'. Appl. Soft Comput., 2018. 67: p. 61–69.
Liu, S., 'Video steganography: recent advances and challenges'. Multimedia Tools Appl., 2026. 85: p. 614.
Duan, S., L. Jia, and P. Li, 'IrisMAE: Structure-aware masked image modeling for iris recognition'. Pattern Recognit., 2026: p. 113493.
Ouda, O., 'BioDeepHash: Generating Consistent Templates for Secure Biometric Authentication'. IEEE Access, 2026.
Garea-Llano, E. and A. Morales-Gonzalez, 'Framework for biometric iris recognition in video, by deep learning and quality assessment of the iris-pupil region'. J. Ambient Intell. Humaniz. Comput., 2023. 14(6): p. 6517–6529.
Ahmadi, N. and M. Nilashi, 'Iris Texture Recognition based on Multilevel 2-D Haar Wavelet Decomposition and Hamming Distance Approach.'. J. Soft Comput. Decis. Support Syst., 2018. 5(3): p. 16.
Ahmadi, N., et al., 'An intelligent method for iris recognition using supervised machine learning techniques'. Opt. Laser Technol., 2019. 120: p. 105701.
Aliyu, M.G., S. Jamel, and M. Danlami, 'Advances in Feature Extraction and Selection for Iris Recognition Systems: A Review'. J. Electron. Voltage Appl., 2025. 6(2): p. 148–165.
Ahmadi, N. and G. Akbarizadeh, 'Iris tissue recognition based on GLDM feature extraction and hybrid MLPNN-ICA classifier'. Neural Comput. Appl., 2020. 32(7): p. 2267–2281.
Ahmadi, N., 'Morphological-Edge Detection Approach for the Human Iris Segmentation.'. J. Soft Comput. Decis. Support Syst., 2019. 6(4): p. 3.
Ahmadi, N. and G. Akbarizadeh, 'Hybrid robust iris recognition approach using iris image pre?processing, two?dimensional gabor features and multi?layer perceptron neural network/PSO'. IET Biom., 2018. 7(2): p. 153–162.
Ahmadi, N. and G. Akbarizadeh, 'Iris recognition system based on canny and LoG edge detection methods'. J. Soft Comput. Decis. Support Syst., 2015. 2(4): p. 26–30.
Ahmadi, N. and G. Akbarizadeh, 'Optimized AI Integration for Superior Iris Texture Analysis', in 2025 7th International Conference on Pattern Recognition and Image Analysis (IPRIA). 2025, IEEE. p. 1–5.
Duan, S., L. Jia, and P. Li, 'IrisMAE: Structure-aware masked image modeling for iris recognition'. Pattern Recognit., 2026: p. 113493.
Wei, J., et al., 'Towards more discriminative and robust iris recognition by learning uncertain factors'. IEEE Trans. Inf. Forensics Secur., 2022. 17: p. 865–879.
Lei, S., et al., 'Attention meta-transfer learning approach for few-shot iris recognition'. Comput. Electr. Eng., 2022. 99: p. 107848.
Ahmadi, N. and G. Akbarizadeh, 'Optimizing power control in cellular and cell-free massive MIMO systems: a SVM/RBF approach'. IEEE Access, 2025. 13: p. 55187–55201.
Nilashi, M., et al., 'Disease diagnosis using machine learning techniques: A review and classification'. J. Soft Comput. Decis. Support Syst., 2020. 7(1): p. 19–30.
Ahmadi, N., 'Review of Terrestrial and Satellite Networks based on Machine Learning Techniques.'. J. Soft Comput. Decis. Support Syst., 2020. 7(3): p. 13.
Nilashi, M., et al., 'Neuromarketing: a review of research and implications for marketing'. J. Soft Comput. Decis. Support Syst., 2020. 7(2): p. 23–31.
Ahmadi, N., et al., 'Power control in massive MIMO networks using transfer learning with deep neural networks', in 2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD). 2022, IEEE. p. 89–93.
Ahmadi, N. and G. Akbarizadeh, 'Machine learning based power control in cellular and cell-free massive MIMO systems'. Sci. Rep., 2026. 16(1): p. 8129.
Ahmadi, N., et al., 'Evaluation of machine learning algorithms on power control of massive MIMO systems', in 2022 13th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP). 2022, IEEE. p. 715–720.
Ahmadi, N. and G. Akbarizadeh, 'Analysing the Influence of Infrastructure and Power Control on Cellular and Cell-Free Massive MIMO Systems: Insights from Machine Learning'. 2024.
Ahmadi, N. and M. Nilashi, 'Does Explainability Enhance the Effectiveness of AI Models in Public Health? The COVID-19 Context.'. J. Soft Comput. Decis. Support Syst., 2024. 11(1): p. 1.
Ahmadi, N. and G. Akbarizadeh, 'Analysing the Influence of Infrastructure and Power Control on Cellular and Cell-Free Massive MIMO Systems: Insights from Machine Learning'. 2024.
Tapia, J.E., et al., 'Forged presentation attack detection for id cards on remote verification systems'. IEEE Trans. Inf. Forensics Secur., 2025. 20: p. 12417.
Yang, J., et al., 'Deep Learning-Based Multimodal Biometric Authentication in Consumer Electronics'. IEEE Trans. Consum. Electron., 2025.
Daugman, J., 'How iris recognition works', in The Essential Guide to Image Processing. 2009, Elsevier. p. 715–739.
Masek, L., 'Recognition of human iris patterns for biometric identification'. 2003.
Zhang, Q., et al., 'Iris recognition based on adaptive optimization log-gabor filter and rbf neural network', in Chinese Conference on Biometric Recognition. 2019, Springer. p. 312–320.
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.