Comparison of Transfer Learning Using VGG16, MobileNetV2, and ResNet50 for Pornography Image Detection
DOI:
https://doi.org/10.59395/ijadis.v6i3.1418Keywords:
Pornography Image Detection, Convolutional Neural Networks (CNN), Skin Color Segmentation , Color Space, Transfer LearningAbstract
The rapid growth of digital technology is vital for the Indonesian Scout to reach and interact with its members. The National Indonesian Scout (Kwarnas) uses the “Ayo Pramuka” social media application to support this. However, such platforms risk exposing users, especially teenagers, to harmful content like pornography. This research applies Computer Vision and Transfer Learning Convolutional Neural Networks (CNNs) to detect pornographic images automatically. The objective is to identify the CNN model (VGG16, MobileNet V2, ResNet 50) with the highest detection accuracy and determine the impact of color space preprocessing. The method includes two stages first, image preprocessing by converting RGB images to HSV and YCbCr second, feature extraction using pre-trained CNNs with freezing and fine-tuning. A dataset of 4060 images was used for training and testing. Without preprocessing, VGG16 achieved the best accuracy of 99.01%. When RGB images were converted to HSV, ResNet 50 produced the highest accuracy of 99.51%. The findings show that combining color space transformation and Transfer Learning CNN significantly improves pornographic content detection in the “Ayo Pramuka” Application, enhancing safe digital engagement for Indonesian Scouts.
Downloads
References
[1] Kwarnas. (2023a). Dasa Karya Gerakan Pramuka. https://pramuka.or.id/dasa-karya/
[2] Kwarnas. (2023b). Visi,Misi,dan Tujuan Gerakan Pramuka. https://pramuka.or.id/visi-misi-dan-tujuan/
[3] Nasrullah, R. (2016). Media Sosial: Perspektif Komunikasi, Budaya, dan Sosioteknologi. Simbiosa Rekatama Media.
[4] Yutifa, U., Santoso, H. B., & Hasibuan, Z. A. (2015). Analisis Penggunaan Media Sosial dalam Penyebaran
[5] Ahmad, S. Z., Ahmad, N., & Bakar, A. R. A. (2019). Reflections of Entrepreneurs of Small and Medium-Sized Enterprises Concerning the Adoption of Social Media and Its Impact on Performance Outcomes: Evidence from the UAE. Telematics and Informatics, 36, 1–17. https://doi.org/10.1016/j.tele.2018.11.007 DOI: https://doi.org/10.1016/j.tele.2017.09.006
[6] Karamizadeh, S., Chaeikar, S. S., & Jolfaeai, A. (2023). Adult Content Image Recognition by Boltzmann Machine Limited and Deep Learning. Evolutionary Intelligence, 16, 1185–1195. https://doi.org/10.1007/s12065-022-00729-8 DOI: https://doi.org/10.1007/s12065-022-00729-8
[7] Setiono, K. (2021). Deteksi Citra Pornografi Memanfaatkan Deep Convolutional Neural Network. Journal of Intelligent Systems and Computation, 3(1), 1–6. DOI: https://doi.org/10.52985/insyst.v3i1.172
[8] Liantoni, F., & Wahyudi, Y. R. (2022). Deteksi Citra Pornografi Menggunakan Skin Color Detection dan Eigenporn Berdasarkan Ruang Warna YCbCr. Jurnal MNEMONIC, 5(2), 145–150. DOI: https://doi.org/10.36040/mnemonic.v5i2.4832
[9] Rahman, A., Tarigan, T., & Sari, R. M. (2022). HSV Color Model and Logical Filter for Human Skin Detection. AIP Conference Proceedings, 2457, 040003. https://doi.org/10.1063/5.0098747 DOI: https://doi.org/10.1063/5.0120025
[10] Jannah, A., & Pratiwi, N. (2025). Deteksi Pornografi pada Citra Karakter Animasi dengan HVS dan YCBCR Menggunakan Naive Bayes. Jurnal Ilmu Penelitian Dan Pembelajaran Informatika, 10(1), 337–344. DOI: https://doi.org/10.29100/jipi.v10i1.5883
[11] Kolkur, S., Kalbande, D., Shimpi, P., Bapat, C., & Jatakia, J. (2017). Human Skin Detection Using RGB, HSV, and YCbCr Color Models. ArXiv Preprint. https://arxiv.org/abs/1708.02694 DOI: https://doi.org/10.2991/iccasp-16.2017.51
[12] Albahli, S. (2023). Transfer Learning for Pornographic Image Detection Using CNN Models. Computer Systems Science & Engineering, 43(2), 701–717. DOI: https://doi.org/10.32604/csse.2022.022723
[13] Aldahoul, N., Omar, M. K., Mohamed, A., Hussain, F., & Rahman, A. (2021a). An Evaluation of Traditional and CNN-Based Feature Descriptors for Cartoon Pornography Detection. IEEE Access, 9, 1–16. https://doi.org/10.1109/ACCESS.2021.3064920 DOI: https://doi.org/10.1109/ACCESS.2021.3064392
[14] Aldahoul, N., Omar, M. K., Mohamed, A., Hussain, F., & Rahman, A. (2021b). Transfer Detection of YOLO to Focus CNN’s Attention on Nude Regions for Adult Content Detection. Symmetry, 13(1), 1–26. https://doi.org/10.3390/sym13010020 DOI: https://doi.org/10.3390/sym13010026
[15] Chen, J., Wu, Z., Zhou, Z., Li, Z., & Liu, X. (2020). A Pornographic Images Recognition Model based on Deep One-Class Classification With Visual Attention Mechanism. IEEE Access, 8, 1–13. https://doi.org/10.1109/ACCESS.2020.2977463 DOI: https://doi.org/10.1109/ACCESS.2020.2988736
[16] Hor, S. L., Phung, S. L., & Bouzerdoum, A. (2022). Deep Active Learning for Pornography Recognition Using ResNet. International Journal of Technology, 13(6), 1261–1270. DOI: https://doi.org/10.14716/ijtech.v13i6.5842
[17] Mazinani, M. R., Hoseini, S. M., & Ahmadi, K. D. (2020). Time-Sensitive Adaptive Model for Adult Image Classification. Computing and Informatics, 39(1), 1282–1310. DOI: https://doi.org/10.31577/cai_2020_6_1282
[18] Moreira, D. C., & Fechine, J. M. (2018). A Machine Learning-based Forensic Discriminator of Pornographic and Bikini Images. Proceedings of the International Joint Conference on Neural Networks (IJCNN), 1–8. https://doi.org/10.1109/IJCNN.2018.8489335 DOI: https://doi.org/10.1109/IJCNN.2018.8489100
[19] Nashrullah, F., Wibowo, S. A., & Budiman, G. (2020). Investigasi Parameter Epoch pada Arsitektur ResNet-50 untuk Klasifikasi Pornografi. Journal of Computer, Electronic, and Telecommunication, 1(1), 1–8.
[20] Nikam, A. V. (2018). Locating and Detecting Nipple for Pornographic Image Identification. Journal of Computer Sciences and Engineering, 6(7), 1343–1347. DOI: https://doi.org/10.26438/ijcse/v6i7.13431347
[21] Phan, D. D., Nguyen, T. A., Le, Q. M., Tran, B. M., & Nguyen, V. V. (2021). A Novel Pornographic Visual Content Classifier based on Sensitive Object Detection. International Journal of Advanced Computer Science and Applications, 12(5), 787–797. https://doi.org/10.14569/IJACSA.2021.0120595 DOI: https://doi.org/10.14569/IJACSA.2021.0120591
[22] Sharma, R. (2020). Using Transfer Learning to Classify Pornographic Images. Proceedings of the Conference on Data Science and Machine Learning Applications (CDMA), 43–46. https://doi.org/10.1109/CDMA47397.2020.00013 DOI: https://doi.org/10.1109/CDMA47397.2020.00013
[23] Surinta, O., & Khamket, T. (2019). Recognizing Pornographic Images using Deep Convolutional Neural Networks. Proceedings of the International Conference on Digital Arts, Media, and Technology, 150–154. https://doi.org/10.1109/ICDAMT.2019.8713477 DOI: https://doi.org/10.1109/ECTI-NCON.2019.8692296
[24] Patterson, J., & Gibson, A. (2017). Deep Learning: A Practitioner’s Approach. O’Reilly Media.
[25] Lin, X., Qin, F., Peng, Y., & Shao, Y. (2021). Fine-Grained Pornographic Image Recognition with Multiple Feature Fusion Transfer Learning. International Journal of Machine Learning and Cybernetics, 12(1), 73–86. https://doi.org/10.1007/s13042-020-01223-5 DOI: https://doi.org/10.1007/s13042-020-01157-9
[26] Naji, S., Jalab, H. A., & Kareem, S. A. (2020). A Survey on Skin Detection in Colored Images. Artificial Intelligence Review, 52(2), 1041–1087. https://doi.org/10.1007/s10462-018-9644-y DOI: https://doi.org/10.1007/s10462-018-9664-9
[27] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems (NIPS), 25, 1097–1105.
[28] Ravanbakhsh, E., Rezaei, M., Namjoo, E., & Choobdar, P. (2022). Comparison between EM and FCM algorithms in skin tone extraction. ArXiv Preprint. https://arxiv.org/abs/2211.09979
[29] Arya, S. J., Asish, A., Shine, B. S. F., Sreelakshmi, J. L., & Varghese, E. (2021). Skin Detection Using YCbCr Colour Space for UAV-Based Disaster Management. In Innovations in Computer Science and Engineering (pp. 633–641). Springer. https://doi.org/10.1007/978-981-33-4543-0_67 DOI: https://doi.org/10.1007/978-981-33-4543-0_67
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Christopher Ade SihWardana, Sani Muhamad Isa
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
Share
Plum Analytics