A Comparative Study of Three Pre-trained Convolutional Neural Networks in the Detection of Violence Against Women

Main Article Content

Ivan Gaytán Aguilar http://orcid.org/0000-0002-4101-5351
Alejandro Aguilar Contreras http://orcid.org/0000-0003-1493-2987
Roberto Alejo Eleuterio http://orcid.org/0000-0002-7580-3305
Eréndira Rendón Lara http://orcid.org/0000-0003-4581-6022
Grisel Miranda Piña http://orcid.org/0000-0001-7122-0658
Everardo E. Granda Guitérrez http://orcid.org/0000-0002-9316-9627


En este documento se presenta una comparación de rendimiento entre 3 modelos de redes CNN pre entrenadas (VGG16, ResNet50 y MobileNet) en la detección de violencia física contra la mujer en video. Para llevar a cabo la clasificación de imágenes que incluyan violencia física contra la mujer y aquellas que no, se recolectaron 2800 imágenes (1400 violentas y 1400 no violentas) de un dataset público y posteriormente fueron divididas en entrenamiento (1200 imágenes), validación (1000 imágenes) y prueba (600 imágenes). Para evaluar su rendimiento, se tomaron en cuenta los valores de exactitud para cada modelo, posicionando a la red MobileNet como el clasificador con mejor rendimiento para esta tarea de clasificación con 89% de exactitud.

Article Details

Como citar
GAYTÁN AGUILAR, Ivan et al. A Comparative Study of Three Pre-trained Convolutional Neural Networks in the Detection of Violence Against Women. CIENCIA ergo-sum, [S.l.], v. 31, n. 2, abr. 2023. ISSN 2395-8782. Disponible en: <https://cienciaergosum.uaemex.mx/article/view/19352>. Fecha de acceso: 29 mayo 2023
Ciencias exactas y aplicadas


Abu, M., Amir, A., Lean, Y. H., Zahri, N. A. H., & Azemi, S. A. (2021). The performance analysis of transfer learning for steel defect detection by using deep learning. Journal of Physics: Conference Series, 1755 (1), 12041.
Alexandrie, G. (2017). Surveillance cameras and crime: A review of randomized and natural experiments. Journal of Scandinavian Studies in Criminology and Crime Prevention, 18 (2), pp. 210–222.
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021). Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 8 (1), pp. 1–74.
Arel, I., Rose, D. C., & Karnowski, T. P. (2010). Deep machine learning-a new frontier in artificial intelligence research [research frontier]. IEEE Computational Intelligence Magazine, 5 (4), pp. 13–18.
Beauxis-Aussalet, E., & Hardman, L. (2014). Visualization of Confusion Matrix for Non-Expert Users (Poster).
Bianculli, M., Falcionelli, N., Sernani, P., Tomassini, S., Contardo, P., Lombardi, M., & Dragoni, A. F. (2020). A dataset for automatic violence detection in videos. Data in Brief, 33, 106587. doi:https://doi.org/10.1016/j.dib.2020.106587
Bilbro, R., Ojeda, T., & Bengfort, B. (2019). Applied text analysis with Python. O'Reilly.
Bisong, E. (2019). JupyterLab Notebooks. In Building Machine Learning and Deep Learning Models on Google Cloud Platform (pp. 49–57). Springer.
Bradski, G. (2000). The OpenCV library. Dr. Dobb’s Journal: Software Tools for the Professional Programmer, 25 (11), pp. 120–123.
Brown, J. B. (2018). Classifiers and their Metrics Quantified. Molecular informatics, 37 (1-2). 1700127, 13 pp. doi.org/10.1002/minf.201700127
Canbek, G., Taskaya Temizel, T. & Sagiroglu, S. Bench (2021) Metrics: a systematic benchmarking method for binary classification performance metrics. Neural Computing & Applications, 33, pp. 14623–14650. doi.org/10.1007/s00521-021-06103-6
Castorena, C. M., Abundez, I. M., Alejo, R., Granda-Gutiérrez, E. E., Rendón, E., & Villegas, O. (2021). Deep neural network for gender-based violence detection on Twitter messages. Mathematics, 9 (8), 807.
Chen, H.-Y., & Su, C.-Y. (2018). An enhanced hybrid MobileNet. 2018 9th International Conference on Awareness Science and Technology (ICAST), pp. 308–312.
Chicco D. & Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics, 21 (6), 13 pp. doi.org/10.1186/s12864-019-6413-7.
Dandamudi, A. G. B., Vasumithra, G., Praveen, G., & Giriraja, C. v. (2020). CNN Based Aerial Image processing model for Women Security and Smart Surveillance. 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT), pp. 1009–1017.
Deng, L., Yu, D., & others. (2014). Deep learning: methods and applications. Foundations and Trends® in Signal Processing, 7 (3–4), pp. 197–387.
Ferrari, G., Torres-Rueda, S., Chirwa, E., Gibbs, A., Orangi, S., Barasa, E., Tawiah, T., Dwommoh Prah, R. K., Hitimana, R., Daviaud, E., & others. (2022). Prevention of violence against women and girls: A cost-effectiveness study across 6 low-and middle-income countries. PLoS Medicine, 19 (3), e1003827.
Fried, T. S. (2003). Violence against Women, Health and Human Rights Violence, Health, and Human Rights.
Gayathri, R. G., Sajjanhar, A., & Xiang, Y. (2020). Image-based feature representation for insider threat classification. Applied Sciences, 10 (14), 4945.
Gujjar, J. P., Kumar, H. R. P., & Chiplunkar, N. N. (2021). Image classification and prediction using transfer learning in Colab notebook. Global Transitions Proceedings, 2 (2), pp. 382–385.
Hanson, A., PNVR, K., Krishnagopal, S., & Davis, L. (2019). Bidirectional Convolutional LSTM for the Detection of Violence in Videos. Leal-Taixé, L., Roth, S. (eds) Computer Vision – ECCV 2018 Workshops. ECCV 2018. Lecture Notes in Computer Science, 11130, 280-295. doi.org/10.1007/978-3-030-11012-3_24
Lea, R. A. (1993). World development report 1993: ‘Investing in Health.’
Luque, A., Carrasco, A., Martín, A., & de Las Heras, A. (2019). The impact of class imbalance in classification performance metrics based on the binary confusion matrix. Pattern Recognition, 91, pp. 216–231.
McQuigg, R. J. A. (2018). Is it time for a UN treaty on violence against women? The International Journal of Human Rights, 22 (3), pp. 305–324.
Miranda, G., Alejo, R., Castorena, C., Rendón, E., Illescas, J., & García, V. (2021). Deep Neural Network to Detect Gender Violence on Mexican Tweets. International Workshop on Artificial Intelligence and Pattern Recognition, pp. 24–32.
Naranjo-Torres, J., Mora, M., Hernández-García, R., Barrientos, R. J., Fredes, C., & Valenzuela, A. (2020). A review of convolutional neural network applied to fruit image processing. Applied Sciences, 10 (10), 3443.
Patel, M. (2021). Real-Time Violence Detection Using CNN-LSTM. ArXiv Preprint ArXiv:2107.07578.
Peixoto, B. M., Avila, S., Dias, Z., & Rocha, A. (2018). Breaking down violence: A deep-learning strategy to model and classify violence in videos. Proceedings of the 13th International Conference on Availability, Reliability and Security, pp. 1–7.
Qureshi, S. (2020). The recognition of violence against women as a violation of human rights in the United Nations system. South Asian Studies, 28 (1).
Roa, J., Jacob, G., Gallino, L., & Hung, P. C. K. (2018). Towards smart citizen security based on speech recognition. 2018 Congreso Argentino de Ciencias de La Informática y Desarrollos de Investigación (CACIDI), pp. 1–6.
Sandhiya, R.; Gokul Prassad, A. R.; Gokul Krishnan, D. & PrajethBalan, S. (2020). Women Abuse Detection in Video Surveillance using Deep Learning. GRD Journals- Global Research and Development Journal for Engineering, 5(4), 5 pp.
Schwartz, M. D. (2000). Methodological issues in the use of survey data for measuring and characterizing violence against women. Violence against Women, 6 (8), pp. 815–838.
Soffer, S., Klang, E., Shimon, O., Barash, Y., Cahan, N., Greenspana, H., & Konen, E. (2021). Deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram: a systematic review and meta-analysis. Scientific Reports, 11 (1), pp. 1–8.
Stančin, I., & Jović, A. (2019). An overview and comparison of free Python libraries for data mining and big data analysis. 2019 42nd International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), pp. 977–982.
Tangirala, S. (2020). Evaluating the impact of GINI index and information gain on classification using decision tree classifier algorithm. International Journal of Advanced Computer Science and Applications, 11 (2), pp. 612–619.
Theckedath, D., & Sedamkar, R. R. (2020). Detecting affect states using VGG16, ResNet50, and SE-ResNet50 networks. SN Computer Science, 1 (2), pp. 1–7.
Vijeikis, R., Raudonis, V., & Dervinis, G. (2022). Efficient violence detection in surveillance. Sensors, 22 (6), 2216.
Vosta, S., & Yow, K.-C. (2022). A CNN-RNN combined structure for real-world violence detection in surveillance cameras. Applied Sciences, 12 (3), 1021.
World Health Organization (1997) Violence against women: Definition and scope of the problem. Geneva, Switzerland: The World Health Organization.
Ye, L., Yan, S., Zhen, J., Han, T., Ferdinando, H., Seppänen, T., & Alasaarela, E. (2022). Physical Violence Detection Based on Distributed Surveillance Cameras. Mobile Networks and Applications, pp. 1–12.