Comparative Evaluation of Deep Learning Embeddings and Classifiers for Gender Classification in Passport Images
DOI:
https://doi.org/10.33474/infotron.v6i1.24670Keywords:
Gender Classification, Passport Images, Image Embedding, VGG-19, Logistic RegressionAbstract
This study presents a comparative evaluation of three deep learning embedding models (VGG-16, VGG-19, and Inception V3) and four machine learning classifiers (Logistic Regression, Support Vector Machine, Neural Network, and Random Forest) for gender classification from passport images. A dataset of 125 passport images (50 male, 75 female) was used. Embeddings were extracted using the pre-trained models and then fed into the classifiers. Performance was measured using accuracy, precision, recall, F1-score, and AUC. The results show that Logistic Regression combined with VGG-19 embeddings achieved the best performance, with an AUC of 0.993, outperforming more complex classifiers such as Neural Networks and Random Forest. This finding suggests that high-quality embeddings can make the classification task nearly linear, reducing the need for complex models. However, the small dataset size and domain-specific nature of passport images limit generalizability, and future research on larger, more diverse datasets is recommended.
References
N. Dwivedi and D. K. Singh, Review of deep learning techniques for gender classification in images, vol. 741. 2019. doi: 10.1007/978-981-13-0761-4_102.
F. Schwarz, K. Schwarz, and R. Creutzburg, “Improving detection of manipulated passport photos - Training course for border control inspectors to detect morphed facial passport photos - Part I: Introduction, state-of-the-art and preparatory tests and experiments,” in Is and T International Symposium on Electronic Imaging Science and Technology, 2021. doi: 10.2352/ISSN.2470-1173.2021.3.MOBMU-136.
S. Gunasekar, J. Ghosh, and A. C. Bovik, “Face detection on distorted images augmented by perceptual quality-aware features,” IEEE Transactions on Information Forensics and Security, vol. 9, no. 12, pp. 2119–2131, 2014, doi: 10.1109/TIFS.2014.2360579.
S. Poornima, N. Sripriya, S. Preethi, and S. Harish, Classification of gender from face images and voice, vol. 1167. 2021. doi: 10.1007/978-981-15-5285-4_11.
R. LeMoyne and T. Mastroianni, Machine learning classification for network centric therapy utilizing the multilayer perceptron neural network. 2020.
K. Yesugade and R. Jadhav, “Implementation of Deep Learning Techniques for Deepfake Classification: A comparative study using ResNet-50 and VGG16,” in 2024 IEEE Pune Section International Conference Punecon 2024, 2024. doi: 10.1109/PuneCon63413.2024.10894868.
H. Gurram, K. Kethineni, D. H. Kommineni, and K. Soumya, “Gender Classification from Thermal Images using CNN,” in 2024 Asia Pacific Conference on Innovation in Technology Apcit 2024, 2024. doi: 10.1109/APCIT62007.2024.10673553.
H. Parikh, S. Patel, and V. Patel, “Transfer learning approach for patch level classification in remote sensing,” in 2019 IEEE 16th India Council International Conference Indicon 2019 Symposium Proceedings, 2019. doi: 10.1109/INDICON47234.2019.9030283.
D. Muduli, S. K. Sharma, D. Pradhan, M. Das, S. Mahapatra, and S. K. sahoo, A Hybrid Deep Learning Approach for COVID-19 Detection: Feature Fusion and SVM Classification, vol. 1153. 2025. doi: 10.1007/978-981-97-8093-8_8.
J. Bozek, I. Kesedzic, L. Novosel, and T. Bozek, “Classification and feature analysis of the Human Connectome Project dataset for differentiating between males and females,” Automatika, vol. 62, no. 1, pp. 109–117, 2021, doi: 10.1080/00051144.2021.1885890.
Z. S. A. Ghrban and N. K. EL Abbadi, “Gender Classification from Face and Eyes Images Using Deep Learning Algorithm,” Journal of Computer Science, vol. 19, no. 3, pp. 345–362, 2023, doi: 10.3844/JCSSP.2023.345.362.
F. waris, F. Da, and S. Liu, “Stacked ensemble learning for facial gender classification using deep learning based features extraction,” Cluster Comput., vol. 27, no. 8, pp. 11491–11513, 2024, doi: 10.1007/s10586-024-04340-7.
M. L. Sai Gayathri, N. Naga Kalyan, P. Vamsidhar, S. Lalitha, A. N. Sree Vaishnavi Neha, and M. Srinivas, “Real-Time Gender Classification from Facial Images Using VGG16 and GoogLeNet Architectures,” in 2025 International Conference on Artificial Intelligence and Data Engineering Aide 2025 Proceedings, 2025, pp. 158–164. doi: 10.1109/AIDE64228.2025.10987491.
G. S. R. Tholeti, D. Ghanta, N. V. S. G. S. S. Chilukuri, and S. Bano, Vocal Source Builds Divergence in Gender Recognition, vol. 783. 2022. doi: 10.1007/978-981-16-3690-5_16.
H. T. A. Ali and D. A. Nasrawi, “Extracting Gender Textual Nuances Using Text Similarity for Gender Classification Improvement,” in Icsintesa 2024 2024 4th International Conference of Science and Information Technology in Smart Administration the Collaboration of Smart Technology and Good Governance for Sustainable Development Goals, 2024, pp. 72–76. doi: 10.1109/ICSINTESA62455.2024.10748083.
P. Shourie, V. Anand, R. Chauhan, G. Verma, and S. Gupta, “A Deep Dive into Gender Classification Using Inception V3: Performance and Insights,” in 2023 Global Conference on Information Technologies and Communications (GCITC), IEEE, Dec. 2023, pp. 1–6. doi: 10.1109/GCITC60406.2023.10426245.
M. Kapse, N. Elangovan, M. Lalkiya, and A. Deshpande, A Comparative Analysis of Machine Learning Algorithms for Image Classification: Evaluating Performance. 2024. doi: 10.1007/978-981-97-2902-9_3.
M. Rathi, A. A. Shah, S. Ali, E. N. Baro, A. W. Memon, and A. Inam, “Binary inception V3 deep learning based image classifier for the detection of breast cancer,” in Aip Conference Proceedings, 2024. doi: 10.1063/5.0214634.
Z. Jiang, “Face gender classification based on convolutional neural networks,” in Proceedings 2020 International Conference on Computer Information and Big Data Applications Cibda 2020, 2020, pp. 120–123. doi: 10.1109/CIBDA50819.2020.00035.
R. K. Yadav, R. Moriwal, and A. Sakhare, “Analysis of Computational Model for Detection and Recognition of Human Activity Using Deep Learning,” in 2024 IEEE International Students Conference on Electrical Electronics and Computer Science Sceecs 2024, 2024. doi: 10.1109/SCEECS61402.2024.10482159.
A. S. Girsang, A. D. Saputra, and V. Yanrie, “Performance Comparison between VGG16 and Inception V3 for Organic Waste and Recyclable Waste Classification,” International Journal of Intelligent Systems and Applications in Engineering, vol. 11, no. 2, pp. 557–563, 2023.
T. Reznychenko, E. Uglickich, and I. Nagy, “Accuracy Comparison of Logistic Regression, Random Forest, and Neural Networks Applied to Real MaaS Data,” in 2024 Smart Cities Symposium Prague Scsp 2024 Proceedings, 2024. doi: 10.1109/SCSP61506.2024.10552715.
G. S. R. Tholeti, D. Ghanta, N. V. S. G. S. S. Chilukuri, and S. Bano, Vocal Source Builds Divergence in Gender Recognition, vol. 783. 2022. doi: 10.1007/978-981-16-3690-5_16.
U. R. Vagalla and J. J. T. Selvaraj, “Customer segmentation of car retails using regularized logistic regression compared with K means clustering,” in Aip Conference Proceedings, 2023. doi: 10.1063/5.0118059.
S. Dong, “Research on the Enhancement and Improvement of Logistic Regression Models,” in 2025 6th International Conference on Electrical Electronic Information and Communication Engineering Eeice 2025, 2025, pp. 492–496. doi: 10.1109/EEICE65049.2025.11033904.
E. Yücesoy, “Gender Recognition from Speech Signal Using CNN, KNN, SVM and RF,” in Procedia Computer Science, 2024, pp. 2251–2257. doi: 10.1016/j.procs.2024.04.213.
H.-S. Gao, A.-L. Guo, X.-D. Yu, and C.-C. Li, “RBF-SVM and its application on network security risk evaluation,” in 2008 International Conference on Wireless Communications Networking and Mobile Computing Wicom 2008, 2008. doi: 10.1109/WiCom.2008.1110.
N. A. Sahadun, H. Haron, and M. R. A. Kadir, “Classification of gender using neural network and support vector machine from bone morphology properties of monkey,” in 2013 IEEE Conference on Open Systems Icos 2013, 2013, pp. 215–220. doi: 10.1109/ICOS.2013.6735077.
A. Olugboja, Optimizing Predictive Performance: A Comparative Study of Machine Learning Algorithms for Classification Tasks, vol. 2501 CCIS. 2025. doi: 10.1007/978-3-031-90341-0_11.
M. Sathish Kumar, T. Sagithya, S. K. Arthi, and K. Subramaniam, “Empirical Evaluation of Activation Functions and Solvers on Neural Network Performance,” in Proceedings of the 9th International Conference on Communication and Electronics Systems Icces 2024, 2024, pp. 1942–1946. doi: 10.1109/ICCES63552.2024.10859295.
A. Mandal, N. Hasan, A. Jain, J. R. Mohanty, and V. Sharma, “Computational Relevance of Model Pruning and Quantization for Low-Powered AI,” in 2025 2nd International Conference on Multidisciplinary Research and Innovations in Engineering Mrie 2025, 2025, pp. 6–10. doi: 10.1109/MRIE66930.2025.11156676.
X. Zhao et al., “U-Net-based VGG19 model for improved facial expression recognition | 基于U-Net架构改进VGG19模型的人脸表情识别方法,” Gongcheng Kexue Xuebao Chinese Journal of Engineering, vol. 47, no. 6, pp. 1272–1284, 2025, doi: 10.13374/j.issn2095-9389.2024.07.24.002.
A. Bakhtiyar, M. A. Ansari, A. Mewada, and D. K. Singh, “From Pixels to People: Deep Learning Breakthroughs in Human Detection,” in Proceedings 2024 IEEE 16th International Conference on Communication Systems and Network Technologies Cicn 2024, 2024, pp. 326–331. doi: 10.1109/CICN63059.2024.10847522.
R. Wang, “Comparative Analysis of Deep Learning Models in Animal Species Recognition: A Case Study on the AFHQ Dataset,” in Aip Conference Proceedings, 2024. doi: 10.1063/5.0223635.
A. A. A. Aboluhom and I. Kandilli, “Face recognition using deep learning on Raspberry Pi,” Computer Journal, vol. 67, no. 10, pp. 3020–3030, 2024, doi: 10.1093/comjnl/bxae066.
Z. Cui, M. Zhang, and Y. Chen, “Deep embedding logistic regression,” in Proceedings 9th IEEE International Conference on Big Knowledge Icbk 2018, 2018, pp. 176–183. doi: 10.1109/ICBK.2018.00031.
S. Rajvanshi, G. Kaur, A. Dhatwalia, Arunima, A. Singla, and A. Bhasin, Research on Problems and Solutions of Overfitting in Machine Learning, vol. 1191 LNEE. 2024. doi: 10.1007/978-981-97-2508-3_47.
J. P. Gygi, S. H. Kleinstein, and L. Guan, “Predictive overfitting in immunological applications: Pitfalls and solutions,” Hum. Vaccin. Immunother., vol. 19, no. 2, 2023, doi: 10.1080/21645515.2023.2251830.
X. Li et al., “From Embeddings to Accuracy: Comparing Foundation Models for Radiographic Classification,” Journal of Imaging Informatics in Medicine, 2025, doi: 10.1007/s10278-025-01747-5.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Rizqi Nur Muhammad, Imam Yuadi, Aliv Faizal Muhammad
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
