Desarrollo de una aplicación web que genere rostros de personas que no existen en el mundo real
DOI:
https://doi.org/10.56183/iberotecs.v4i1.639Palavras-chave:
Generación de rostros; aprendizaje profundo, algoritmos, matriz de confusión, métricas de rendimiento.Resumo
Con el creciente desarrollo de la Generative Adversarial Network (GAN), la generación de imágenes son un desafío emocionante en el campo del aprendizaje profundo y la inteligencia artificial. A nivel internacional se han desarrollado diversos trabajos relacionados a modelos de redes generativas antagónicas, pero una brecha significativa persiste en la falta de comparativas entre diferentes algoritmos. La capacidad de generar imágenes inexistentes que se asemejen en gran medida a las imágenes del mundo real es interesante para muchos casos de uso. En la presente investigación se propone desarrollar una aplicación web basada en redes neuronales preexistentes, utilizando la tecnología generativa antagónica para generar rostros de personas. En este estudio, se consideró como población de estudio a los 5.000 rostros que pertenecen el conjunto de datos FFHQ Face Dataset (2.500 rostro mujer) y (2.500 rostro de hombre). Las técnicas que fueron empleadas están basadas en dos modelos utilizando los siguientes algoritmos: Generative Adversarial Network (GAN) y Red Adversarial Generativa Convolucional Profunda (DCGAN). Las mediciones estadísticas de la matriz de confusión como resultado de la clasificación se utilizaron como métricas de rendimiento. Los resultados permiten concluir que el modelo (DCGAN) es el mejor método de clasificación, debido a su mejor predicción de los valores obtenidos de verdaderos positivos, y verdaderos negativos, además, la media de la precisión del modelo fue de 85,02%, superior al otro modelo. La aplicación desarrollada ha cumplido con éxito el objetivo principal de generar rostros humanos a partir de algoritmos de inteligencia artificial.
Referências
Adjabi, I., Ouahabi, A., Benzaoui, A., & Taleb-Ahmed, A. (2020). Past, Present, and Future of Face Recognition: A Review. Electronics, 9(8), 1188. https://doi.org/10.3390/electronics9081188
Ahmed, S. R., Sonuç, E., Ahmed, M. R., & Duru, A. D. (2022). Analysis Survey on Deepfake detection and Recognition with Convolutional Neural Networks. 2022 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), 1–7. https://doi.org/10.1109/HORA55278.2022.9799858
Akcay, S., Atapour-Abarghouei, A., & Breckon, T. P. (2019). GANomaly: Semi-supervised Anomaly Detection via Adversarial Training. Computer Vision – ACCV 2018, 622–637. https://doi.org/10.1007/978-3-030-20893-6_39
Alqahtani, H., Kavakli-Thorne, M., & Kumar, G. (2021). Applications of Generative Adversarial Networks (GANs): An Updated Review. Archives of Computational Methods in Engineering, 28(2), 525-552. https://doi.org/10.1007/s11831-019-09388-y
Andersen, T., Byrne, D. V., & Wang, Q. J. (2021). How Digital Food Affects Our Analog Lives: The Impact of Food Photography on Healthy Eating Behavior. Frontiers in Psychology, 12, 634261. https://doi.org/10.3389/fpsyg.2021.634261
Bian, Y., & Xie, X.-Q. (2021). Generative chemistry: drug discovery with deep learning generative models. Journal of Molecular Modeling, 27(3), 71. https://doi.org/10.1007/s00894-021-04674-8
Chen, S., Zhang, D., Yang, L., & Chen, P. (2019). Age-invariant Face Recognition Based on Sample Enhancement of Generative Adversarial Networks. 2019 6th International Conference on Systems and Informatics (ICSAI), 388–392. https://doi.org/10.1109/ICSAI48974.2019.9010229
Chong, M. J., Lee, H.-Y., & Forsyth, D. (2021). StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGAN (arXiv:2111.01619). arXiv. https://doi.org/10.48550/arXiv.2111.01619
Hao, S., Wen, M., & Cho, K. (2022). Method for Generating Panoramic Textures for 3D Face Reconstruction Based on the 3D Morphable Model. NATO Advanced Science Institutes Series E: Applied Sciences, 12(19), 10020. https://doi.org/10.3390/app121910020
Jia, N., Zheng, C., & Sun, W. (2019). A Model of Emotional Speech Generation Based on Conditional Generative Adversarial Networks. 2019 11th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), 1, 106–109. https://doi.org/10.1109/IHMSC.2019.00033
Khosravy, M., Nakamura, K., Hirose, Y., Nitta, N., & Babaguchi, N. (2022). Model Inversion Attack by Integration of Deep Generative Models: Privacy-Sensitive Face Generation From a Face Recognition System. IEEE Transactions on Information Forensics and Security, 17, 357–372. https://doi.org/10.1109/TIFS.2022.3140687
Kislinger, L., & Kotrschal, K. (2021). Hunters and Gatherers of Pictures: Why Photography Has Become a Human Universal. Frontiers in Psychology, 12, 654474. https://doi.org/10.3389/fpsyg.2021.654474
Kumar, A. S., Tesfaye Jule, L., Ramaswamy, K., Sountharrajan, S., Yuuvaraj, N., & Gandomi, A. H. (2021). Chapter 12 - Analysis of false data detection rate in generative adversarial networks using recurrent neural network. In A. Solanki, A. Nayyar, & M. Naved (Eds.), Generative Adversarial Networks for Image-to-Image Translation (pp. 289–312). Academic Press. https://doi.org/10.1016/B978-0-12-823519-5.00012-9
Letenkov, M., & Levonevskiy, D. (2020). Fast Face Features Extraction Based on Deep Neural Networks for Mobile Robotic Platforms. Interactive Collaborative Robotics, 200–211. https://doi.org/10.1007/978-3-030-60337-3_20
Liu, X., Zou, Y., Xie, C., Kuang, H., & Ma, X. (2019). Bidirectional Face Aging Synthesis Based on Improved Deep Convolutional Generative Adversarial Networks. Information. An International Interdisciplinary Journal, 10(2), 69. https://doi.org/10.3390/info10020069
Liu, Z., & Wu, J. (2019). A Complex Image Restoration Method Based on Generating Adversarial Neural Networks. Proceedings of the 2019 4th International Conference on Mathematics and Artificial Intelligence, 105–109. https://doi.org/10.1145/3325730.3325765
Liu, Y., Fu, Z., & Li, T. (2023). How Can Artificial Intelligence Transform the Future Design Paradigm and Its Innovative Competency Requisition: Opportunities and Challenges. En H. Degen, S. Ntoa, & A. Moallem (Eds.), HCI International 2023 – Late Breaking Papers (pp. 131-148). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-48057-7_9
Marra, F., Saltori, C., Boato, G., & Verdoliva, L. (2019). Incremental learning for the detection and classification of GAN-generated images. 2019 IEEE International Workshop on Information Forensics and Security (WIFS), 1-6. https://doi.org/10.1109/WIFS47025.2019.9035099
Nandhini Abirami, R., Durai Raj Vincent, P. M., Srinivasan, K., Tariq, U., & Chang, C.-Y. (2021). Deep CNN and Deep GAN in Computational Visual Perception-Driven Image Analysis. Complexity, 2021. https://doi.org/10.1155/2021/5541134
Neves, J. C., Tolosana, R., Vera-Rodriguez, R., Lopes, V., Proença, H., & Fierrez, J. (2020). GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection. IEEE Journal of Selected Topics in Signal Processing, 14(5), 1038–1048. https://doi.org/10.1109/JSTSP.2020.3007250
Olszanowski, M., Pochwatko, G., Kuklinski, K., Scibor-Rylski, M., Lewinski, P., & Ohme, R. K. (2014). Warsaw set of emotional facial expression pictures: a validation study of facial display photographs. Frontiers in Psychology, 5, 1516. https://doi.org/10.3389/fpsyg.2014.01516
Pehlivan, H., Dalva, Y., & Dundar, A. (2023). StyleRes: Transforming the Residuals for Real Image Editing With StyleGAN. 1828-1837. https://openaccess.thecvf.com/content/CVPR2023/html/Pehlivan_StyleRes_Transforming_the_Residuals_for_Real_Image_Editing_With_StyleGAN_CVPR_2023_paper.html
Perez, L., & Wang, J. (2017). The Effectiveness of Data Augmentation in Image Classification using Deep Learning. In arXiv [cs.CV]. arXiv. http://arxiv.org/abs/1712.04621
Raut, R., Pathak, P. D., Sakhare, S. R., & Patil, S. (2023). Generative Adversarial Networks and Deep Learning: Theory and Applications. CRC Press. https://play.google.com/store/books/details?id=P_GyEAAAQBAJ
Sarker, I. H. (2021). Machine Learning: Algorithms, Real-World Applications and Research Directions. SN Computer Science, 2(3), 160. https://doi.org/10.1007/s42979-021-00592-x
Street, S. E., Morgan, T. J. H., Thornton, A., Brown, G. R., Laland, K. N., & Cross, C. P. (2018). Human mate-choice copying is domain-general social learning. Scientific Reports, 8(1), 1715. https://doi.org/10.1038/s41598-018-19770-8
Sutedja, I., & Septhia, J. (2022). The Usage of Generative Adversarial Network for Image: A Systematic Literature Review. 2022 International Conference on Information Management and Technology (ICIMTech), 307–311. https://doi.org/10.1109/ICIMTech55957.2022.9915093
Talahua, J. S., Buele, J., Calvopiña, P., & Varela-Aldás, J. (2021). Facial Recognition System for People with and without Face Mask in Times of the COVID-19 Pandemic. Sustainability: Science Practice and Policy, 13(12), 6900. https://doi.org/10.3390/su13126900
Tariq, S., Lee, S., Kim, H., Shin, Y., & Woo, S. S. (2019). GAN is a friend or foe? a framework to detect various fake face images. Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing, 1296–1303. https://doi.org/10.1145/3297280.3297410
Wang, X., Guo, H., Hu, S., Chang, M.-C., & Lyu, S. (2022). GAN-generated Faces Detection: A Survey and New Perspectives. In arXiv [cs.CV]. arXiv. http://arxiv.org/abs/2202.07145
Xiao, Y., Lu, M., & Fu, Z. (2020). Covered Face Recognition Based on Deep Convolution Generative Adversarial Networks. Artificial Intelligence and Security, 133–141. https://doi.org/10.1007/978-3-030-57884-8_12
Xu, X., & Wang, X. (2022). Human face cartoon image generation based on CycleGAN. 5th International Conference on Computer Information Science and Application Technology (CISAT 2022), 12451, 516–520. https://doi.org/10.1117/12.2656569
Yu, C., & Pei, H. (2021). Face recognition framework based on effective computing and adversarial neural network and its implementation in machine vision for social robots. Computers & Electrical Engineering, 92, 107128. https://doi.org/10.1016/j.compeleceng.2021.107128
Zeng, J., He, X., Li, S., Wu, L., & Wang, J. (2022). Virtual Face Animation Generation Based on Conditional Generative Adversarial Networks. 2022 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML), 580–583. https://doi.org/10.1109/ICICML57342.2022.10009693
Zhang, P., Wang, Y., Kumar, N., Jiang, C., & Shi, G. (2022). A Security- and Privacy-Preserving Approach Based on Data Disturbance for Collaborative Edge Computing in Social IoT Systems. IEEE Transactions on Computational Social Systems, 9(1), 97–108. https://doi.org/10.1109/TCSS.2021.3092746
Downloads
Publicado
Edição
Seção
Licença
Copyright (c) 2024 María Quezada-García, Kevin Cajamarca-Castillo, Wilmer Rivas-Asanza, Bertha Mazón-Olivo
Este trabalho está licenciado sob uma licença Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
