A HYBRID INTELLIGENCE FRAMEWORK FOR PERSONALIZED EYEWEAR RECOMMENDATION: INTEGRATING HAAR CASCADE LOCALIZATION WITH A GENETICALLY TUNED CNN CLASSIFIER
DOI:
https://doi.org/10.31849/3cy8ft64Keywords:
Face Shape Classification, Hybrid Intelligence, Convolutional Neural Network, Genetic Algorithm, Hyperparameter OptimizationAbstract
A hybrid intelligence framework was presented to improve eyewear recommendations through robust face shape classification. A Haar Cascade Classifier was integrated for initial facial localization, alongside a Convolutional Neural Network (CNN) based on the InceptionV3 architecture for the primary classification task. A pseudo-labeling technique was utilized to refine the dataset, which elevated the initial model to 88.54% test accuracy. Furthermore, the CNN's hyperparameters were systematically tuned using a Genetic Algorithm (GA). This evolutionary tuning process yielded a significant performance boost, culminating in a final classification accuracy of 97.65%. It was concluded that the synergistic combination of advanced preprocessing, data refinement, and a genetically optimized deep learning model provided a highly accurate solution for personalized recommendation systems.
References
[1] V. Ramadhan, M. W. Sardjono, M. Cahyanti, R. Swedia, M. Ridwan, and D. Septian, “Klasifikasi Bentuk Bingkai (Frame) Kacamata Menggunakan CNN dengan Arsitektur Inception V3 dan Augmented Reality Berbasis Android,” Journal of System and Computer Engineering (JSCE) ISSN, vol. 5, no. 2, p. 204, Apr. 2024, doi: https://doi.org/10.61628/jsce.v5i2.1292.
[2] J. Zhao, M. Zhang, C. He, X. Xie, and J. Li, “A novel facial attractiveness evaluation system based on face shape, facial structure features and skin,” Cogn Neurodyn, vol. 14, no. 5, pp. 643–656, Oct. 2020, doi: 10.1007/s11571-020-09591-9.
[3] A. Sukumaran and T. Brindha, “Optimal feature selection with hybrid classification for automatic face shape classification using fitness sorted Grey wolf update,” Multimed Tools Appl, vol. 80, no. 17, pp. 25689–25710, Jul. 2021, doi: 10.1007/s11042-021-10710-9.
[4] J. Khatib Sulaiman Dalam No, N. Dakhil Hasan, and A. M. Abdulazeez, “Face Recognition Based on Deep Learning: A Comprehensive Review,” Indonesian Journal of Computer Science, vol. 13, no. 3, Jun. 2024, doi: https://doi.org/10.33022/ijcs.v13i3.4037.
[5] F. T. Nugroho and E. I. Sela, “Deteksi Citra Wajah Menggunakan Algoritma Haar Cascade Classifier,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 4, no. 1, pp. 37–44, Dec. 2023, doi: 10.57152/malcom.v4i1.988.
[6] E. Setyaningsih and L. Widodo, “Comparative Analysis of Haar Cascade Classifier, Dlib, and Mediapipe for Face Recognition Analisis Perbandingan Haar Cascade Classifier, Dlib, dan Mediapipe untuk Pengenalan Wajah,” ELECTRON Jurnal Ilmiah Teknik Elektro, vol. 6, no. 1, May 2025, doi: https://doi.org/10.33019/electron.v6i1.240.
[7] N. Karlupia, P. Mahajan, P. Abrol, and P. K. Lehana, “A Genetic Algorithm Based Optimized Convolutional Neural Network for Face Recognition,” International Journal of Applied Mathematics and Computer Science, vol. 33, no. 1, pp. 21–31, Mar. 2023, doi: 10.34768/amcs-2023-0002.
[8] T. Hidayat, I. A. Astuti, A. Yaqin, A. Phuk Tjilen, and T. Arifianto, “Grouping of Image Patterns Using Inceptionv3 For Face Shape Classification,” Journal on Informatics Visualization, vol. 7, Dec. 2023, doi: http://dx.doi.org/10.62527/joiv.7.4.1743.
[9] A. Emmanuel, C. Tio, and D. C. Tio, “Face shape classification using Inception v3,” ArXiv, Nov. 2019, doi: 10.48550/arXiv.1911.07916.
[10] P. Kage, J. C. Rothenberger, P. Andreadis, and D. I. Diochnos, “A Review of Pseudo-Labeling for Computer Vision,” ArXiv, May 2025, [Online]. Available: http://arxiv.org/abs/2408.07221
[11] H. Pham, Z. Dai, Q. Xie, M.-T. Luong, and Q. V. Le, “Meta Pseudo Labels,” ArXiv, Mar. 2021, [Online]. Available: http://arxiv.org/abs/2003.10580
[12] W. Hussain et al., “Ensemble genetic and CNN model-based image classification by enhancing hyperparameter tuning,” Sci Rep, vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-024-76178-3.
[13] P. Kalaiarasi and P. E. Rani, “A Novel Approach for Optimization of Convolution Neural Network with Particle Swarm Optimization and Genetic Algorithm for Face Recognition,” International Journal on Recent and Innovation Trends in Computing and Communication, vol. 11, no. 4, pp. 215–223, Mar. 2023, doi: 10.17762/ijritcc.v11i4s.6531.
[14] P. Ghosh, S. Jana, S. Ghosh, and R. Dhar, “Hyperparameter Optimization in Deep Learning Techniques for Multimodal Biometric Verification,” Devotion Journal of Research Progress, vol. 6, no. 9, 2025, doi: https://doi.org/10.59188/devotion.v6i9.25529.
[15] Niten Lama, “Face Shape Dataset,” Kaggle, Jan. 2020.
[16] Project, “Face Shape Classification Dataset,” Roboflow Universe, Sep. 2023.
[17] W. C. Cheng, H. C. Hsiao, Y. Q. Hong, and D. Y. Wang, “Masked face recognition based on facenet and genetic algorithm,” International Journal of Applied Science and Engineering, vol. 20, no. 3, 2023, doi: 10.6703/IJASE.202309_20(3).005.
[18] I. T. Aruleba and Y. Sun, “Deep Learning and Genetic Algorithms Approach for Age Estimation Based on Facial Images,” International Journal of Computer Theory and Engineering, vol. 16, no. 4, pp. 127–133, 2024, doi: 10.7763/IJCTE.2024.V16.1360.
[19] F. Fatimatuzzahra, L. Lindawati, and S. Soim, “Development of Convolutional Neural Network Models to Improve Facial Expression Recognition Accuracy,” Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, vol. 10, no. 2, pp. 279–289, Jun. 2024, doi: 10.26555/jiteki.v10i2.28863.
[20] O. Oladipo, E. O. Omidiora, and V. C. Osamor, “A novel genetic-artificial neural network based age estimation system,” Sci Rep, vol. 12, no. 1, Dec. 2022, doi: 10.1038/s41598-022-23242-5.
[21] P. Probst and B. Bischl, “Tunability: Importance of Hyperparameters of Machine Learning Algorithms,” Journal of Machine Learning Research, vol. 20, pp. 1–32, 2019, doi: https://doi.org/10.48550/arXiv.1802.09596Focustolearnmore.
[22] J. A Ilemobayo et al., “Hyperparameter Tuning in Machine Learning: A Comprehensive Review,” Journal of Engineering Research and Reports, vol. 26, no. 6, pp. 388–395, Jun. 2024, doi: 10.9734/jerr/2024/v26i61188.
[23] D. Passos and P. Mishra, “A tutorial on automatic hyperparameter tuning of deep spectral modelling for regression and classification tasks,” Apr. 15, 2022, Elsevier B.V. doi: 10.1016/j.chemolab.2022.104520.
[24] X. Wang and Y. Li, “Facial Recognition System Based on Genetic Algorithm Improved ROI-KNN Convolutional Neural Network,” Appl Bionics Biomech, vol. 2022, Oct. 2022, doi: 10.1155/2022/7976856.
[25] M. Sam’an, Safuan, and M. Munsarif, “Convolutional neural network hyperparameters for face emotion recognition using genetic algorithm,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 33, no. 1, pp. 442–449, Jan. 2024, doi: 10.11591/ijeecs.v33.i1.pp442-449.
[26] V. Kachitvichyanukul, “Comparison of Three Evolutionary Algorithms: GA, PSO, and DE,” Industrial Engineering and Management Systems, vol. 11, no. 3, pp. 215–223, Sep. 2012, doi: 10.7232/iems.2012.11.3.215.
[27] M. Munsarif, E. Noersasongko, P. N. Andono, and M. A. Soeleman, “Improving convolutional neural network based on hyperparameter optimization using variable length genetic algorithm for english digit handwritten recognition,” International Journal of Advances in Intelligent Informatics, vol. 9, no. 1, pp. 66–78, Mar. 2023, doi: 10.26555/ijain.v9i1.881.
[28] S. Degaonkar and A. Agarkar, “Real Time Face Mask Detection Using Inception-V3,” Int J Res Appl Sci Eng Technol, vol. 11, no. 11, pp. 973–979, Nov. 2023, doi: 10.22214/ijraset.2023.56652.
[29] G. Elvis, “Optimization of CNN Pipelines for Low-light Image Recognition Using Genetic Algorithms,” SSRN Electronic Journal, Sep. 2020, doi: 10.2139/ssrn.5289444.
[30] M. S. Nidom, “Haar Cascade Classifier and Adaboost Algorithm for Face Detection with the Viola-Jones Method,” Transactions on Informatics and Data Science, vol. 2, no. 1, pp. 15–26, Mar. 2025, doi: 10.24090/tids.v2i1.12276.
[31] D. R. Rochmawati, “Deteksi Wajah Dengan Metode Haar Cascade Menggunakan OpenCV (Face Detection With Haar Cascade Method Using OpenCV),” Journal Politeknik Pajajaran, Sep. 2024, doi: 10.59820/tekomin.v3i1.293.
[32] H. M. Al-Dabbas, R. A. Azeez, and A. E. Ali, “Two Proposed Models for Face Recognition: Achieving High Accuracy and Speed with Artificial Intelligence,” Engineering, Technology and Applied Science Research, vol. 14, no. 2, pp. 13706–13713, Apr. 2024, doi: 10.48084/etasr.7002.
[33] H. Amri, “Real-Time Face Attendance System Using CNN Mobilenet and MTCNN,” JURNAL TEKNOLOGI DAN OPEN SOURCE, vol. 8, no. 1, pp. 164–179, Jun. 2025, doi: 10.36378/jtos.v8i1.4403.
[34] N. A. Mohd Ariffin, U. A. Gimba, and A. Musa, “Face Detection based on Haar Cascade and Convolution Neural Network (CNN),” Journal of Advanced Research in Computing and Applications, vol. 38, no. 1, pp. 1–11, Mar. 2025, doi: 10.37934/arca.38.1.111.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 ZONAsi: Jurnal Sistem Informasi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
CC BY-SA 4.0
Attribution-ShareAlike 4.0
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
