Face Gender Classification for Public Facility Access Control using EfficientNet with Penalized-Entropy Loss

Sabrina Adinda  Sari; Faidhil Nugrah  Ramadhan Ahmad; Miftahul  Adnan Rasyid; I Gede  Manggala Putra; Fauzan  Ramadhan

doi:10.52436/1.jutif.2026.7.3.5675

Authors

Sabrina Adinda Sari School of Computing, Telkom University, Indonesia
Faidhil Nugrah Ramadhan Ahmad School of Computing, Telkom University, Indonesia
Miftahul Adnan Rasyid School of Computing, Telkom University, Indonesia
I Gede Manggala Putra School of Computing, Telkom University, Indonesia
Fauzan Ramadhan School of Computing, Telkom University, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.3.5675

Keywords:

CCTV recordings, EfficientNet-B0, face mask, gender classification, overconfidence, Penalized Entropy Loss

Abstract

Access to public facilities that are restricted based on gender, such as toilets and changing rooms, requires a strict security system because there are still many cases of abuse by irresponsible parties if only gender signs are relied upon. CCTV integrated with facial recognition is becoming more sophisticated every day, but it is limited if the face is covered by attributes such as masks. This is because the less visible the area is, the more difficult it is for the model to determine the label. To overcome this, this study proposes a gender classification approach for faces that may be covered by accessories such as masks, by adding Penalized Entropy loss as a loss function to the EfficientNet-B0 model. This loss function adds a penalty for incorrect predictions even if they are fairly accurate. The evaluation results show that the proposed model, with a penalty weight of 0.5, improved the accuracy by 3% from 90% to 93%. The experimental results show that the determination of the penalty weight has a significant impact on model performance, where a weight of 0.5 produces optimal performance because it provides a balance between penalizing overconfident predictions and the model's ability to maintain relevant feature discrimination; too small a weight does not sufficiently suppress overconfidence, while too large a weight actually reduces classification ability. The proposed method has demonstrated improvements in generalization and reduced overconfidence in gender classification systems. This method contributes to the development of reliable biometric systems suitable for uncontrolled real-world environments.

Downloads

Download data is not yet available.

References

N. C. Weley, F. Y. P. Amboro, and T. D. Seroja, “Behind Closed Lenses: Analyzing the Efficacy of Personal Data Protection Laws in Combatting Hidden Cameras,” J. Judic. Rev., vol. 26, no. 1, pp. 89–112, 2024, doi: 10.37253/jjr.v26i1.9158.

S. Herodotou and F. Hao, “Spying on the Spy: Security Analysis of Hidden Cameras,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 13983 LNCS, pp. 345–362, 2023, doi: 10.1007/978-3-031-39828-5_19.

W. N. Hartzog and E. Selinger, “Scholarly Commons at Boston University School of Law Privacy Nicks : How the Law Normalizes Surveillance,” 2024.

Di. Dao, M. Salman, and Y. Noh, “DeepDeSpy: A Deep Learning-Based Wireless Spy Camera Detection System,” IEEE Access, vol. 9, pp. 145486–145497, 2021, doi: 10.1109/ACCESS.2021.3121254.

S. A. Sari and W. F. Al Maki, “Masked Face Images Based Gender Classification using Hybrid Bat Algorithm Optimized Bagging,” 5th Int. Conf. Artif. Intell. Inf. Commun. ICAIIC 2023, pp. 91–96, 2023, doi: 10.1109/ICAIIC57133.2023.10067008.

S. Adinda and M. Dwi, “Modified Hybrid Pooling on FaceNet Embedding to Enhance a Surveillance-Based Suspect Detection System.”

E. Ahmad Khorsheed and Z. Ali Nayef, “Face Recognition Algorithms: A Review,” Acad. J. Nawroz Univ., vol. 11, no. 3, pp. 202–207, 2022, doi: 10.25007/ajnu.v11n3a1432.

S. A. Sari and M. D. Sulistiyo, “Suspect Identification Based on Facial Recognition from CCTV Using Hybrid Bat Algorithm,” Int. Conf. Electr. Eng. Comput. Sci. Informatics, pp. 205–210, 2024, doi: 10.1109/EECSI63442.2024.10776490.

W. Ali, W. Tian, S. U. Din, D. Iradukunda, and A. A. Khan, Classical and modern face recognition approaches: a complete review, vol. 80, no. 3. Multimedia Tools and Applications, 2021.

S. Sandhya, A. Balasundaram, and A. Shaik, “Deep Learning Based Face Detection and Identification of Criminal Suspects,” Comput. Mater. Contin., vol. 74, no. 2, pp. 2331–2343, 2023, doi: 10.32604/cmc.2023.032715.

H. Du, H. Shi, D. Zeng, X. P. Zhang, and T. Mei, “The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances,” ACM Comput. Surv., vol. 54, no. 10, 2022, doi: 10.1145/3507902.

D. Fu et al., “Unsupervised Pre-training for Person Re-identification,” pp. 14750–14759.

M. Ye, J. Shen, G. Lin, T. Xiang, L. Shao, and S. C. H. Hoi, “Deep Learning for Person Re-Identification: A Survey and Outlook,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 6, pp. 2872–2893, 2022, doi: 10.1109/TPAMI.2021.3054775.

K. Mohan, A. Seal, O. Krejcar, and A. Yazidi, “FER-net: facial expression recognition using deep neural net,” Neural Comput. Appl., vol. 33, no. 15, pp. 9125–9136, 2021, doi: 10.1007/s00521-020-05676-y.

M. Sajjad et al., “A comprehensive survey on deep facial expression recognition: challenges, applications, and future guidelines,” Alexandria Eng. J., vol. 68, pp. 817–840, 2023, doi: 10.1016/j.aej.2023.01.017.

J. Mao et al., “POSTER++: A simpler and stronger facial expression recognition network,” Pattern Recognit., vol. 157, 2025, doi: 10.1016/j.patcog.2024.110951.

A. Garain, B. Ray, P. K. Singh, A. Ahmadian, N. Senu, and R. Sarkar, “GRA_Net: A Deep Learning Model for Classification of Age and Gender from Facial Images,” IEEE Access, vol. 9, pp. 85672–85689, 2021, doi: 10.1109/ACCESS.2021.3085971.

S. Teja Chavali, C. Tej Kandavalli, T. M. Sugash, and R. Subramani, “Smart Facial Emotion Recognition with Gender and Age Factor Estimation,” Procedia Comput. Sci., vol. 218, no. 2022, pp. 113–123, 2022, doi: 10.1016/j.procs.2022.12.407.

E. Kim, D. Bryant, D. Srikanth, and A. Howard, “Age Bias in Emotion Detection: An Analysis of Facial Emotion Recognition Performance on Young, Middle-Aged, and Older Adults,” AIES 2021 - Proc. 2021 AAAI/ACM Conf. AI, Ethics, Soc., pp. 638–644, 2021, doi: 10.1145/3461702.3462609.

G. Gingin, M. Dwi, M. Arzaki, and E. Rachmawati, “Classifying Gender Based on Face Images Using Vision Transformer,” vol. 8, no. March, pp. 18–25, 2024.

M. Oulad-Kaddour, H. Haddadou, C. C. Vilda, D. Palacios-Alonso, K. Benatchba, and E. Cabello, “Deep Learning-Based Gender Classification by Training With Fake Data,” IEEE Access, vol. 11, no. October, pp. 120766–120779, 2023, doi: 10.1109/ACCESS.2023.3328210.

A. Garain, B. Ray, P. K. Singh, A. Ahmadian, N. Senu, and R. Sarkar, “GRA_Net: A Deep Learning Model for Classification of Age and Gender from Facial Images,” IEEE Access, vol. 9, pp. 85672–85689, 2021, doi: 10.1109/ACCESS.2021.3085971.

M. J. Al Dujaili, H. T. S. Al Rikabi, N. K. Abed, and I. R. N. Al Rubeei, “Gender Recognition of Human from Face Images Using Multi-Class Support Vector Machine (SVM) Classifiers,” Int. J. Interact. Mob. Technol., vol. 17, no. 8, pp. 113–134, 2023, doi: 10.3991/ijim.v17i08.39163.

J. G. Thanikkal, A. K. Dubey, and M. T. Thomas, “An Efficient Mobile Application for Identification of Immunity Boosting Medicinal Plants using Shape Descriptor Algorithm,” Wirel. Pers. Commun., vol. 131, no. 2, pp. 1189–1205, 2023, doi: 10.1007/s11277-023-10476-3.

L. Martinelli et al., “Face Masks During the COVID-19 Pandemic: A Simple Protection Tool With Many Meanings,” Front. Public Heal., vol. 8, no. January, pp. 1–12, 2021, doi: 10.3389/fpubh.2020.606635.

S. Rab, M. Javaid, A. Haleem, and R. Vaishya, “Face masks are new normal after COVID-19 pandemic,” Diabetes Metab. Syndr. Clin. Res. Rev., vol. 14, no. 6, pp. 1617–1619, 2020, doi: 10.1016/j.dsx.2020.08.021.

Oluwatosin Seyi Oyebanji et al., “Enhancing breast cancer detection accuracy through transfer learning: A case study using efficient net,” World J. Adv. Eng. Technol. Sci., vol. 13, no. 1, pp. 285–318, 2024, doi: 10.30574/wjaets.2024.13.1.0415.

M. Behzadpour, B. L. Ortiz, E. Azizi, and K. Wu, “Breast Tumor Classification Using EfficientNet Deep Learning Model,” pp. 1–19, 2024, [Online]. Available: http://arxiv.org/abs/2411.17870.

A. O. Ibraheem, “Regularizing cross entropy loss via minimum entropy and K-L divergence,” pp. 1–5, 2025, [Online]. Available: http://arxiv.org/abs/2501.13709.

D. Feng et al., “Penalized Entropy: a novel loss function for uncertainty estimation and optimization in medical image classification,” Proc. - IEEE Symp. Comput. Med. Syst., vol. 2022-July, pp. 306–310, 2022, doi: 10.1109/CBMS55023.2022.00061.

W. Kim and Y. Sung, “An Adaptive Entropy-Regularization Framework for Multi-Agent Reinforcement Learning,” Proc. Mach. Learn. Res., vol. 202, pp. 16829–16852, 2023.

G. Jagatap, A. Joshi, A. B. Chowdhury, S. Garg, and C. Hegde, “Adversarially Robust Learning via Entropic Regularization,” Front. Artif. Intell., vol. 4, pp. 1–19, 2022, doi: 10.3389/frai.2021.780843.

R. Jin, H. Li, J. Pan, W. Ma, and J. Lin, “Face Recognition Based on MTCNN and FaceNet,” 2021, [Online]. Available: www.aaai.org.

S. S. Khan, D. Sengupta, A. Ghosh, and A. Chaudhuri, “MTCNN++: A CNN-based face detection algorithm inspired by MTCNN,” Vis. Comput., vol. 40, no. 2, pp. 899–917, 2024, doi: 10.1007/s00371-023-02822-0.

S. G. C, K. H. S, S. Shirahatti, and S. R. Bangari, “Face Recognition System for Real Time Applications Using Svm Combined With Facenet and Mtcnn,” Int. J. Electr. Eng. Technol., vol. 12, no. 6, pp. 328–335, 2021, doi: 10.34218/IJEET.12.6.2021.031.

P. Khairunnisa, W. E. Putra, W. Yitong, A. Jufrizal, and M. N. A. Makmum, “Convolutional Neural Networks Using EfficientNetB0 Architecture and Hyperparameters on Skin Disease Classification,” Public Res. J. Eng. Data Technol. Comput. Sci., vol. 2, no. 2, pp. 127–137, 2025, doi: 10.57152/predatecs.v2i2.1569.

Q. L. MingxingTan, “EfﬁcientNet: RethinkingModelScalingforConvolutionalNeuralNetworks,” Int. Conf. Mach. Learn. Long Beach, Calif., 2019.

A. G. Howard et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” 2017, [Online]. Available: http://arxiv.org/abs/1704.04861.

H. L. Potgieter, C. Mouton, and M. H. Davel, “Impact of Batch Normalization on Convolutional Network Representations,” Commun. Comput. Inf. Sci., vol. 2326 CCIS, pp. 235–252, 2025, doi: 10.1007/978-3-031-78255-8_14.