Automatic Gender Recognition System Through Eye Image Analysis: Using Hybrid Pre-Trained Convolutional Neural Network-Haar Cascade Classifier
DOI:
https://doi.org/10.47701/xy69g360Keywords:
Eye Image, Convolutional Neural Network, Haar Cascade Classifier, Gender RecognitionAbstract
The development of intelligent systems based on digital image processing has encouraged the application of automatic gender identification in various fields, such as security and surveillance. However, in real-world conditions such as CCTV footage or the use of personal protective equipment, a person's face is often partially covered, making full-face identification methods less effective. In this study, we propose an automatic gender recognition system based on eye image analysis by combining a pretrained Convolutional Neural Network (CNN) and a Haar Cascade Classifier. CNN is used to perform gender classification, while Haar Cascade is used to detect and extract the eye area as a Region of Interest (ROI). Two recommended CNN architectures, VGG16 and MobileNetV2, are compared to evaluate the system's performance. The preprocessing process includes image resizing, pixel value normalization, and data augmentation to improve the generalization of a model. Evaluation is carried out using accuracy, precision, recall, and f1-score metrics. The test results show that VGG16 provides the best performance with an accuracy of 96%, while MobileNetV2 achieves an accuracy of 94%. Furthermore, VGG16 also demonstrated superior recognition capabilities for minority classes. Implementation results demonstrate that the proposed approach works effectively under partially obscured face conditions, potentially making it applicable to camera-based surveillance systems with visual impairments.
References
Abdalrady, N. A., & Aly, S. (2020). Fusion of multiple simple convolutional neural networks for gender classification. International Conference on Innovative Trends in Communication and Computer Engineering, 251–252.
Arnita, Marpaung, F., Aulia, F., Suryani, N., & Nabila, R. C. (2022). Computer vision dan pengolahan citra digital. Pustaka Aksara.
Bahit, M., Utami, N. P., Candra, H. K., Supit, Y., & Ramadhan, A. (2023). Validation of the Haar Cascade classification method in face detection. Journal of Informatics and Telecommunication Engineering, 233–243.
Cimtay, Y., & Yilmaz, G. N. (2021). Gender classification from eye images by using pretrained convolutional neural networks. The Eurasia Proceedings of Science, Technology, Engineering & Mathematics, 39–44.
Elgendy, M. (2020). Deep learning for vision systems. Manning Publications Co.
Firdaus, R., Satria, J., & Baidarus. (2022). Klasifikasi jenis kelamin berdasarkan gambar mata dengan menggunakan algoritma convolutional neural network (CNN). Computer Science and Information Technology, 267–273.
Ghrban, Z. S., & Abbadi, N. K. (2023). Gender classification from face and eyes images using deep learning algorithm. Journal of Computer Science, 345–362.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. The MIT Press.
Gumilang, M. S., & Avianto, D. (2023). Recognition of real-time handwritten characters using convolutional neural network architecture. Jurnal Teknik Informatika, 1143–1150.
Jung, S.-G., An, J., Kwak, H., Salminen, J., & Jansen, B. J. (2018). Assessing the accuracy of four popular face recognition tools for inferring gender, age, and race. Proceedings of the Twelfth International AAAI Conference on Web and Social Media, 624–627.
Ke, Q., Liu, J., Bennamoun, M., An, S., Sohel, F., & Boussaid, F. (2018). Computer vision for human-machine learning. Computer Vision for Assistive Healthcare, 127–145.
Lakshmi, D., Janaki, R., Subashini, V., Kumar, K. S., Aurelia, C. A., & Ananya, S. T. (2023). Prediction of age, gender, and ethnicity using Haar Cascade algorithm in convolutional neural networks. Proceedings of World Conference on Artificial Intelligence: Advances and Applications, 205–219.
LeCun, Y., & Bengio, Y. (1998). Convolutional networks for images, speech, and time series. Association for Computing Machinery.
Mamyrbayev, O., Toleu, A., Tolegen, G., Mekebayev, N., & Pham, D. (2020). Neural architectures for gender detection and speaker identification. Cogent Engineering, 1–13.
Mohri, M., Rostamizadeh, A., & Talwalkar, A. (2018). Foundations of machine learning. The MIT Press.
Mostafa, S., & Wu, F.-X. (2021). Diagnosis of autism spectrum disorder with convolutional autoencoder and structural MRI images. Neural Engineering Techniques for Autism Spectrum Disorder, 23–38.
Narayanan, A., & K, S. (2019). Gender detection and classification from fingerprints using pixel count. International Conference on System Energy and Environment, 1–5.
Natun, N. C., Santhia, M. A., & Kaesmetan, Y. R. (2024). Identifikasi pengenalan wajah berdasarkan jenis kelamin menggunakan metode convolutional neural network (CNN). Journal of Technology and Informatics, 50–57.
Nengsih, W. (2020). CNN modelling untuk deteksi wajah berbasis gender menggunakan Python. Jurnal Politeknik Caltex Riau, 190–199.
Pandimurugan, D. V., Jain, A., & Sinha, Y. (2020). IoT-based face recognition for smart applications using machine learning. Proceedings of the Third International Conference on Intelligent Sustainable Systems, 1263–1266.
Pradana, A. I., & Wijiyanto. (2024). Identifikasi jenis kelamin otomatis berdasarkan mata manusia menggunakan convolutional neural network (CNN) dan Haar Cascade classifier. Jurnal Teknologi Terapan, 502–511.
Ramadini, F. L., & Haryatmi, E. (2022). Penggunaan metode Haar Cascade classifier dan LBPH untuk pengenalan wajah secara realtime. INFOTEKJAR, 1–8.
Salam, S., B, S., Hasnawati, & Muhaemin, M. (2020). Pengetahuan dasar seni rupa. Badan Penerbit Universitas Negeri Makassar.
Saraswati, N. M., Hariyono, R. C., & Chandra, D. (2023). Face recognition menggunakan metode Haar Cascade classifier dan local binary pattern histogram. Media Elektrik, 6–11.
Scendoni, R., Kelmendi, J., Ribeiro, I. L., CingolaniI, M., MiccoI, F. D., & Cameriere, R. (2023). Anthropometric analysis of orbital and nasal parameters for sexual dimorphism: New anatomical evidences in the field of personal identification through a retrospective observational study. National Library of Medicine, 1–11.
Serna, I., Pena, A., Morales, A., & Fierrez, J. (2020). InsideBias: Measuring bias in deep networks and application to face gender biometrics. International Conference on Pattern Recognition, 3720–3721.
Singh, H. (2019). Practical machine learning and image processing for facial recognition, object detection, and pattern recognition using Python. Apress.
Topaloglu, M., & Ekmekci, S. (2017). Gender detection and identifying one’s handwriting with handwriting analysis. Expert Systems With Applications, 236–243.
Vani, A., Raajan, R. N., Haretha Winmalar, D., & Sudharsan, R. (2020). Using the Keras model for accurate and rapid gender identification through detection of facial features. Proceedings of the Fourth International Conference on Computing Methodologies and Communication, 572–574.
Wicaksono, R. D., Pratama, F. I., & Budianita, A. (2024). Klasifikasi gender berdasarkan citra mata manusia menggunakan algoritma convolutional neural network. Prosiding Seminar Nasional Sains dan Teknologi, 308–313.
Xue, Z., Rajaraman, S., Long, R., Antani, S., & Thoma, G. R. (2018). Gender detection from spine X-ray images using deep learning. International Symposium on Computer-Based Medical Systems, 54–55.
Yingge, H., Ali, I., & Lee, K.-Y. (2020). Deep neural networks on chip—A survey. International Conference on Big Data and Smart Computing, 589–592.
Yulina, S. (2021). Penerapan Haar Cascade classifier dalam mendeteksi wajah dan transformasi citra grayscale menggunakan OpenCV. Jurnal Politeknik Caltex Riau, 100–109.
Zeni, L. F., & Jung, C. (2018). Real-time gender detection in the wild using deep neural networks. Conference on Graphics, Patterns and Images, 118–125.
