Enhancing facial recognition in surveillance systems through embedded super-resolution
DOI:
https://doi.org/10.17533/udea.redin.20240203Keywords:
super-resolution, face enhancement, computer vision, surveillance, machine learningAbstract
This document details the implementation of a sub-pixel convolutional neural network designed to enhance the resolution of face images. The model uses a series of filters to progressively increase the number of pixels, estimating the necessary information for new pixels from the original image and training derived from 22000 synthetic images produced by adversarial neural networks. Within the context of surveillance and related applications, the trained convolutional network exhibits beneficial characteristics. For instance, it can be deployed within a device to achieve higher-resolution images than those the physical camera can produce. This research underscores the feasibility of such a device through the implementation and evaluation of the network on the NVIDIA Jetson TX2 embedded system. The findings demonstrate the model's practicality for real-time surveillance applications and its ability to produce superior-quality images compared to several interpolation methods, as determined by an exhaustive testing process measuring various attributes of the generated images.
Downloads
References
Z. Bojkovic and A. Samcovic, “Face detection approach in neural network based method for video surveillance,” in 2006 8th Seminar on Neural Network Applications in Electrical Engineering, Belgrade, Serbia, 2006. [Online]. Available: https://doi.org/10.1109/NEUREL.2006.341172
H. Qezavati, B. Majidi, and M. Manzuri, “Partially covered face detection in presence of headscarf for surveillance applications,” in 4th International Conference on Pattern Recognition and Image Analysis (IPRIA), Tehran, Iran, 2019. [Online]. Available: https://doi.org/10.1109/PRIA.2019.8786004
J. Harikrishnan, A. Sudarsan, A. Sadashiv, and R. Ajai, “Vision-face recognition attendance monitoring system for surveillance using deep learning technology and computer vision,” in International Conference on Vision Towards Emerging Trends in Communication and Networking (ViTECoN),, Vellore, India, 2019. [Online]. Available: https://doi.org/10.1109/ViTECoN.2019.8899418
Y. Wang, T. Bao, C. Ding, and M. Zhu, “Face recognition in real-world surveillance videos with deep learning method,” in 2nd International Conference on Image, Vision and Computing (ICIVC), Chengdú, China, 2017. [Online]. Available: https://doi.org/10.1109/ICIVC.2017.7984553
Q. Zhao and S. Wang, “Real-time face tracking in surveillance videos on chips for valuable face capturing,” in International Conference on Artificial Intelligence and Computer Engineering (ICAICE),, Beijing, China, 2020. [Online]. Available: https://doi.org/10.1109/ICAICE51518.2020.00060
A. Makhfoudi, S. Almaadeed, A. Bouridane, G. Sexton, and R. Jiang, “Visualization of faces from surveillance videos via face hallucination,” in International Conference on Control, Decision and Information Technologies (CoDIT), Metz, France, 2014. [Online]. Available: https://doi.org/10.1109/CoDIT.2014.6996982
Z. Chen, Q. He, W. Pang, and Y. Li, “Frontal face generation from multiple pose-variant faces with cgan in real-world surveillance scene,” in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada, 2018. [Online]. Available: https://doi.org/10.1109/ICASSP.2018.8462648
A. Khan, M. Khan, F. Obaid, S. Jadoon, M. Khan, and M. Sikandar, “A novel multi-frame super resolution algorithm for surveillance camera image reconstruction,” in First International Conference on Anti-Cybercrime (ICACC), Riyadh, Saudi Arabia, 2015. [Online]. Available: https://doi.org/10.1109/Anti-Cybercrime.2015.7351950
F. Mokhayeri, E. Granger, and G. Bilodeau, “Synthetic face generation under various operational conditions in video surveillance,” in IEEE International Conference on Image Processing (ICIP), Quebec City, QC, Canada, 2015. [Online]. Available: https://doi.org/10.1109/ICIP.2015.7351567
S. Park, M. Park, and M. Kang, “Super-resolution image reconstruction: a technical overview,” in presented at IEEE Aerospace Conference, 2003. [Online]. Available: https://doi.org/10.1109/MSP.2003.1203207
L. Ziwei, W. Chengdong, C. Dongyue, Q. Yuanchen, and W. Chunping, “Overview on image super resolution reconstruction,” in 26th Chinese Control and Decision Conference (2014 CCDC), Changsha, China, 2014. [Online]. Available: https://doi.org/10.1109/CCDC.2014.6852498
IEEE, “Ieee standard computer dictionary: A compilation of ieee standard computer glossaries,” in presented at IEEE Std 610, 1991. [Online]. Available: https://doi.org/10.1109/IEEESTD.1991.106963
P. Shamsolmoali, M. E. Celebi, and R. Wang, “Deep learning approaches for real-time image super-resolution,” Neural Computing and Applications, vol. 32, Jul. 15, 2020. [Online]. Available: https://doi.org/10.1007/s00521-020-05176-z
X. Niu, “An overview of image super-resolution reconstruction algorithm,” in 11th International Symposium on Computational Intelligence and Design (ISCID), Hangzhou, China, 2018. [Online]. Available: https://doi.org/10.1109/ISCID.2018.10105
T. Cui, L. Tang, J. Nan, and Z. Li, “Space target super-resolution based on low-complex convolutional networks,” in IEEE International Conference on Signal, Information and Data Processing (ICSIDP), Chongqing, China, 2019. [Online]. Available: https://doi.org/10.1109/ICSIDP47821.2019.9173516
H. Huang, X. Fan, C. Qi, and S. Zhu, “A learning-based pocs algorithm for face image super-resolution reconstruction,” in International Conference on Machine Learning and Cybernetics, Guangzhou, China, 2005. [Online]. Available: https://doi.org/10.1109/ICMLC.2005.1527837
X. Yang, W. Wu, K. Liu, P. W. Kim, A. K. Sangaiah, and et al., “Long-distance object recognition with image super resolution: A comparative study,” in presented at IEEE Access, 2018. [Online]. Available: https://doi.org/10.1109/ACCESS.2018.2799861
X. Hu, X. Liu, Z. Wang, X. Li, W. Peng, and G. Cheng, “Rtsrgan: Real-time super-resolution generative adversarial networks,” in Seventh International Conference on Advanced Cloud and Big Data (CBD), Suzhou, China, 2019. [Online]. Available: https://doi.org/10.1109/CBD.2019.00064
Y. Lee, J. Yun, Y. Hong, J. Lee, and M. Jeon, “Accurate license plate recognition and super-resolution using a generative adversarial networks on traffic surveillance video,” in IEEE International Conference on Consumer Electronics - Asia (ICCE-Asia), JeJu, Korea (South), 2018. [Online]. Available: https://doi.org/10.1109/ICCE-ASIA.2018.8552121
S. Kim and P. Bindu, “Realizing real-time deep learning-based super-resolution applications on integrated gpus,” in 15th IEEE International Conference on Machine Learning and Applications (ICMLA), Anaheim, CA, USA, 2016. [Online]. Available: https://doi.org/10.1109/ICMLA.2016.0122
W. Shi, J. Caballero, F. Huszár, J. Totz, A. Aitken,R. Bishop, andet al., “Real-time single image and videosuper-resolution using an efficient sub-pixel convolutionalneural network,” inIEEE Conference on Computer Visionand Pattern Recognition (CVPR), 2016. [Online]. Available:https://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Shi_Real-Time_Single_Image_CVPR_2016_paper.html
AI Free. This person does not exist. Accessed Oct. 18, 2021. [Online].Available:https://thispersondoesnotexist.com/
T. Karras, S. Laine, M. Aittala, J. Hellsten, J. Lehtinen, and T. Aila,“Analyzing and improving the image quality of stylegan,”Arxiv,vol. 2, Mar. 23, 2020. [Online]. Available:https://doi.org/10.48550/arXiv.1912.04958
Cascade Classifier, Open Source Computer Vision 3.4.20, 2022.
Face recognition. GitHub. Accessed Nov. 13, 2013. [Online].Available:https://github.com/ageitgey/face_recognition
J. E. Sanabria-Moyano, M. D. P. Roa-Avella, and O. I. Lee-Pérez,“Tecnología de reconocimiento facial y sus riesgos en los derechoshumanos,”Revista Criminalidad, vol. 64, no. 3, 2022. [Online].Available:https://doi.org/10.47741/17943108.366
M. Márquez, C. A. Vargas, and H. Arguello, “Compact spatio-spectralalgorithm for single image super-resolution in hyperspectral imaging,”Ingeniería e Investigación, vol. 36, no. 3, Sep-Dec.2016 2016. [Online]. Available:https://doi.org/10.15446/ing.investig.v36n3.54267
S. Karalasingham, R. C. Deo, D. Casillas-Pérez, N. Raj, and S. Salcedo-Sanz, “Downscaling surface albedo to higher spatial resolutions with an image super-resolution approach and proba-v satellite images,” in IEEE Access, 2023. [Online]. Available: https://doi.org/10.1109/ACCESS.2023.3236253
M. A. Talab, S. Awang, and S. A. d. M. Najim, “Super-low resolution face recognition using integrated efficient sub-pixel convolutional neural network (espcn) and convolutional neural network (cnn),” in IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS), Selangor, Malaysia, 2019. [Online]. Available: https://doi.org/10.1109/I2CACIS.2019.8825083
A. Leftheriotis, A. Tzomaka, D. Danopoulos, G. Lentaris, G. Theodoridis, and D. Soudris, “Evaluating versal acap and conventional fpga platforms for ai inference,” in 12th International Conference on Modern Circuits and Systems Technologies (MOCAST), Athens, Greece, 2023. [Online]. Available: https://doi.org/10.1109/MOCAST57943.2023.10176615
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Revista Facultad de Ingeniería Universidad de Antioquia
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Revista Facultad de Ingeniería, Universidad de Antioquia is licensed under the Creative Commons Attribution BY-NC-SA 4.0 license. https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en
You are free to:
Share — copy and redistribute the material in any medium or format
Adapt — remix, transform, and build upon the material
Under the following terms:
Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
NonCommercial — You may not use the material for commercial purposes.
ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
The material published in the journal can be distributed, copied and exhibited by third parties if the respective credits are given to the journal. No commercial benefit can be obtained and derivative works must be under the same license terms as the original work.
Twitter