REDE NEURAL PROFUNDA DE MÚLTIPLAS ENTRADAS COM DADOS 3D APLICADOS AO RECONHECIMENTO FACIAL
Palavras-chave:
Reconhecimento facial, pix2vertex, SIFTResumo
Neste trabalho é proposta uma metodologia utilizando rede neural multientrada para realizar o reconhecimento facial de indivíduos a partir das características 3D extraídas de imagens frontais. Para a extração das características 3D as imagens foram inicialmente submetidas à rede pix2vertex para realizar a reconstrução 3D da geometria facial de cada indivíduo. Após a reconstrução 3D foram extraídos 275 pontos, contendo as seguintes informações: coordenadas x, y e z, e os descritores de pontos chave do algoritmo SIFT (Scale Invariant Feature Transform). E por fim, essas informações são processadas em uma rede neural artificial de múltiplas entradas para a previsão da classificação de cada indivíduo. A avaliação dos resultados mostra que a rede foi capaz de classificar corretamente os indivíduos com uma precisão de 95,79% no conjunto de validação.
Downloads
Referências
ADJABI, I.; OUAHABI, A.; BENZAOUI, A.; TALEB-AHMED, A. Past, Present, and Future of Face Recognition: A Review. Electronics, v. 9, n. 8, 2020. DOI: https://doi.org/10.3390/electronics9081188.
APPLE. Sobre a tecnologia avançada do Face ID: Saiba como o Face ID ajuda a proteger as informações no iPhone e no iPad Pro. Março de 2020. Disponível em: https://support.apple.com/pt-br/HT208108. Acesso em: 2 nov. 2023.
ARAÚJO, F. H. D. et al. Redes neurais convolucionais com tensorflow: teoria e pratica. In: ESCOLA REGIONAL DE INFORMÁTICA DO PIAUÍ. 3., Livro Anais - Artigos e Muinicursos, v. 1, n.. 1, p. 382-406, 2017.
BHARDWAJ, S.; GOHEL, H.; NAMUDURI, S. A Multiple-Input Deep Neural Network Architecture for Solution of One-Dimensional Poisson Equation. IEEE Antennas and Wireless Propagation Letters, v. 18, n. 11, p. 2244-2248, Nov. 2019. DOI: https://doi.org/10.1109/LAWP.2019.2933181
CHOLLET, F. et al. Keras, 2023. Disponível em: https://keras.io/. Acesso em: 26 nov. 2023.
DANIEAU, F. et al. Automatic Generation and Stylization of 3D Facial Rigs. In: IEEE CONFERENCE ON VIRTUAL REALITY AND 3D USER INTERFACES (VR), 2019, Osaka, Japan. Anais [...]. Osaka, Japan, 2019. p. 784-792. DOI: https://doi.org/10.1109/VR.2019.8798208
SILVA, F. A.; PEREIRA, D. R.; SILVA, J. F. C.; ARTERO, A. O.; PITERI, M. A. TSRS - A new approach for traffic sign recognition using the SIFT algorithm. Journal of Urban and Environmental Engineering, v. 2, n. 2, p. 1-5, 2017.
HE, K.; ZHANG, X.; REN, S.; SUN, J. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. In: IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, Santiago, Chile. Anais [...] Santiago, Chile, 2015. p. 1026-1034. DOI: https://doi.org/10.1109/ICCV.2015.123
HU, X.; NIU, P.; WANG, J.; ZHANG, X. A Dynamic Rectified Linear Activation Units. IEEE Access, v. 7, p. 180409-180416, 2019. DOI: https://doi.org/10.1109/ACCESS.2019.2959036
JAIN, A. Understanding Convolutional Neural Networks (CNNs) with an Example on the MNIST Dataset. Disponível em: https://medium.com/@abhishekjainindore24/understanding-convolutional-neural-networks-cnns-with-an-example-on-the-mnist-dataset-a64815843685. Acesso em: 28 set. 2024.
JING, Y.; LU, X.; GAO, S. 3D face recognition: A comprehensive survey in 2022. Computational Visual Media. v. 9, p. 657–685, 2023. DOI: https://doi.org/10.1007/s41095-022-0317-1.
JONES, E. et al. SciPy, 2001. Disponível em: https://docs.scipy.org/doc/scipy/reference/
generated/scipy.special.softmax.html. Acesso em: 15 fev. 2023.
KARPATHY, A. A Recipe for Training Neural Networks 2019. Disponível em: http://karpathy.github.io/2019/04/25/recipe/. Acesso em: 8 mar. 2023.
KOENDERINK, J. J. The structure of images. Biological Cybernetics, v. 50, p. 363-396, 1984. DOI: https://doi.org/10.1007/BF00336961
KOVAL, S. I. Data preparation for neural network data analysis. In: IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), 2018, Moscow and St. Petersburg, Russia. Anais [...] Moscow and St. Petersburg, Russia, 2018. p. 898-901. DOI: https://doi.org/10.1109/EIConRus.2018.8317233.
KURNIANGGORO, L.; PASSALACQUA, D. Facemark API for OpenCV, 15 jun. 2020. Disponível em: https://github.com/kurnianggoro/GSOC2017. Acesso em: 1 abr. 2022.
LEAL, J. F. S. Criação de Modelos Faciais 3D Através de Fotografias. In: INSTITUTO SUPERIOR DE ENGENHARIA DO PORTO, 2017. Livro Anais – Artigos e Mini cursos, v. 1, n. 1, p. 5-17.
LINDEBERG, T. Scale-space theory: a basic tool for analyzing structures at different scales, Journal of applied Statistics, v. 21, n. 1-2, p. 225-270, 1994. DOI: https://doi.org/10.1080/757582976.
LIVIERIS, I. E.; DAFNIS, S. D.; P., G. K.; KALIVAS, D. P. A Multiple-Input Neural Network Model for Predicting Cotton Production Quantity: A Case Study. Algorithms, v. 13, n. 11, 2020. DOI: https://doi.org/10.3390/a13110273
LOWE, D. G. Object recognition from local scale-invariant features. In: IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, Kerkyra,1999, Greece. Anais […].Kerkyra, Greece, 1999. p. 1150-1157. DOI: https://doi.org/10.1109/ICCV.1999.790410
LOWE, D. G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, v. 60, n. 2, p. 91-110, 2004. DOI: https://doi.org/10.1023/B:VISI.0000029664.99615.94.
MASUD, M.; MUHAMMAD, G.; ALHUMYANI, H.; ALSHAMRANI, S. S.; CHEIKHROUHOU, O.; IBRAHIM, S.; HOSSAIN, M. S. Deep learning-based intelligent face recognition in IoT-cloud environment. Computer Communications, n. 152, p. 215–222, 2020. DOI: https://doi.org/10.1016/j.comcom.2020.01.050.
MEDIAPIPE. FaceMesh. Disponível em: https://google.github.io/mediapipe/solutions/face_mesh.html. Acesso em: 20 jan. 2022.
MIKOŁAJCZYK, A.; GROCHOWSKI, M. Data augmentation for improving deep learning in image classification problem. In: INTERNATIONAL INTERDISCIPLINARY PHD WORKSHOP (IIPhDW), 2018, Poland. Anais [...]. Poland, 2018. p. 117-122. DOI: https://doi.org/10.1109/IIPHDW.2018.8388338.
MIKOŁAJCZYK, K.; SCHMID, C. A performance evaluation of local descriptors. IEEE Transaction on Pattern Analysis and Machine Intelligence, v. 27, n. 10, p. 1615-1630, 2005. DOI: https://doi.org/10.1109/TPAMI.2005.188.
PIZARRO, D.; BARTOLI, A. Global optimization for optimal generalized procrustes analysis. In: Conference on Computer Vision and Pattern Recognition (CVPR), 2011, Colorado Springs, USA. Anais [...]. Colorado Springs, USA, 2011. p. 2409-2415. DOI: https://doi.org/10.1109/CVPR.2011.5995677.
RAZA, S. E. A. et al. MIMO-Net: A multi-input multi-output convolutional neural network for cell segmentation in fluorescence microscopy images. In: IEEE 14TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2017), 2017. Anais […]. Melbourne, Australia: IEEE, 2017. p. 337-340.
SAMET, R.; SHOKOUH, G. S.; BATUHAN, K. B. An Efficient Pose Tolerant Face Recognition Approach. Lecture Notes in Computer Science. Transactions on Computer Science XXVI. p. 1-12, 2016. DOI: https://doi.org/10.1007/978-3-662-49247-5_10.
REN, S.; CAO, X.; WEI, Y.; SUN, J. Face Alignment at 3000 FPS via Regressing Local Binary Features. In: IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, 2014, Columbus, USA. Anais [...] Columbus, USA, 2014. p. 1685-1692. DOI: https://doi.org/10.1109/CVPR.2014.218.
SELA, M.; RICHARDSON, E.; KIMMEL, R. Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation. In: IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, Venice, Italy. Anais [...] Venice, Italy, 2017. p. 1585-1594. DOI: https://doi.org/10.1109/ICCV.2017.175.
SYMANOVICH, S. How does facial recognition work? 2023. Disponível em: https://us.norton.com/internetsecurity-iot-how-facial-recognition-software-works.html. Acesso em: 2 nov. 2023.
SZEGEDY, C. et al. Inception-v4, inception-ResNet and the impact of residual connections on learning. In: AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE (AAAI'17).31. AAAI Press, 2017, San Francisco, California, USA. Proceedings […]. San Francisco, CA, 2017, p.4278–4284. DOI: https://doi.org/10.1609/aaai.v31i1.11231
TATAR, A.; HAGHIGHI, M.; ZEINIJAHROMI, A. Experiments on image data augmentation techniques for geological rock type classification with convolutional neural networks. Journal of Rock Mechanics and Geotechnical Engineering. v. 17, n. 1, p. 106-125, 2025 DOI: https://doi.org/10.1016/j.jrmge.2024.02.015.
THOMAZ, C. E. FEI Face Database, mar. 2006. Disponível em: https://fei.edu.br/~cet/facedatabase.html. Acesso em: 17 dez. 2022.
VIOLA, P.; JONES, M. Rapid object detection using a boosted cascade of simple features. In: IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR). Kauai, USA Proceedings […]. Kauai, 2001. p. I-I.
WÜBBENHORST, T.; WERMKE, F.; MEFFERT, B. Synchronization of Multiple Time-of-Flight Cameras Using Photodiodes. IEEE SENSORS, Rotterdam, Netherlands, 2020, p. 1-4. DOI: https://doi.org/10.1109/SENSORS47125.2020.9278774.
ZALEVSKY, Z.; BULLER, G. S.; CHEN, T.; COHEN, M.; BARTON-GRIMLEY, R. Light detection and ranging (lidar): introduction. Journal of the Optical Society of America B. v. 38, n. 11, 2021. DOI: https://doi.org/10.1364/JOSAB.445791.
ZHANG, Z. Microsoft Kinect Sensor and Its Effect. IEEE MultiMedia, v. 19, n. 2, pp. 4-10, 2012. DOI: https://doi.org/10.1109/MMUL.2012.24.