Enhancing Low-Resolution Facial Images for Forensic Identification Using ESRGAN
DOI:
https://doi.org/10.61132/ijmeal.v1i4.156Keywords:
deep learning, ESRGAN, facial identification, forensic images, super-resolutionAbstract
This research is motivated by the challenges in facial identification for forensic investigations due to poor image quality, especially from low-resolution CCTV recordings. Images with noise, low lighting, and suboptimal angles often hinder accurate facial recognition. This study aims to examine the effectiveness of the Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) method in enhancing the quality of forensic facial images. The methodology consists of three main stages: data preparation of low-resolution facial images, applying the ESRGAN model to enhance image resolution, and evaluating the results using metrics such as PSNR and SSIM. The findings reveal that ESRGAN significantly improves the visual details of facial images, thereby supporting better facial identification processes. These results have important implications for leveraging deep learning technology to facilitate image analysis in forensic contexts. However, challenges such as extreme noise presence require further development of methods to achieve more optimal outcomes.
References
Agafonov, V. (2014). Super-resolution approach to increasing the resolution of image. Lecture Notes in Computer Science. https://doi.org/10.1007/978-3-319-11854-3_29
Akhyar, F., Novamizanti, L., & Riantiarni, T. (2022). Sistem inspeksi cacat pada permukaan kayu menggunakan model deteksi objek YOLOv5. Elkomika, 10(4). https://doi.org/10.26760/elkomika.v10i4.990
Alexander, A., Botti, F., Dessimoz, D., & Drygajlo, A. (2004). The effect of mismatched recording conditions on human and automatic speaker recognition in forensic applications. Forensic Science International, 146(2–3), 127–137. https://doi.org/10.1016/j.forsciint.2004.09.078
Chudasama, V., & Upla, K. P. (2019). ISRGAN: Improved super-resolution using generative adversarial networks. Lecture Notes in Electrical Engineering, 631. https://doi.org/10.1007/978-3-030-17795-9_9
Chyan, P. (2017). Penerapan image enhancement algorithm untuk meningkatkan kualitas citra tak bergerak. Jurnal Teknik Informatika, 9(3), 45–50.
Domingues, P., & Rosário, A. F. (2019). Deep learning-based facial detection and recognition in still images for digital forensics. Proceedings of the 14th International Conference on Availability, Reliability and Security (ARES). https://doi.org/10.1145/3339252.3340107
Evison, M. (2014). Forensic facial analysis. In Encyclopedia of Forensic and Legal Medicine (pp. 561–568). https://doi.org/10.1007/978-1-4614-5690-2_170
Gonbadani, M. M. A., & Abbasfar, A. (2020, August 4). Combined single and multi-frame image super-resolution. Proceedings of the Iranian Conference on Electrical Engineering (ICEE). https://doi.org/10.1109/ICEE50131.2020.9260802
Ikhsal, M. F., Dermawan, B. A., & Adam, R. I. (2023). Peningkatan deteksi kecelakaan di jalan raya menggunakan Real-ERSGAN pada citra CCTV persimpangan jalan. Journal of Artificial Intelligence and Cybernetics (JAIC), 7(1). http://dx.doi.org/10.30871/jaic.v7i1.5562
Kim, D., & Kyung, R. (2022). Improving image quality using deep learning-based super-resolution. Proceedings of the IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON). https://doi.org/10.1109/IEMCON56893.2022.9946503
Nugraha, R. S. (2024). Peningkatan kualitas untuk deteksi objek pada citra satelit menggunakan metode super resolution dan YOLOv5. Universitas Sriwijaya Repository. http://repository.unsri.ac.id/id/eprint/153933
Parekh, D., Maiti, A., & Jain, V. (2022). Image super-resolution using GAN: A study. Proceedings of the 6th International Conference on Trends in Electronics and Informatics (ICOEI). https://doi.org/10.1109/ICOEI53556.2022.9777129
Patmawati, N. P., Arifianto, A., & Ramadhani, K. N. (2019). Quality image enhancement from low resolution camera using convolutional neural network. Proceedings of the 7th International Conference on Information and Communication Technology (ICOICT). https://doi.org/10.1109/ICOICT.2019.8835273
Pearline, A. (2016). Face recognition under varying blur in an unconstrained environment. International Journal of Research in Engineering and Technology, 5(4), 25–30. https://doi.org/10.15623/IJRET.2016.0504070
Prabhu, B. V. B., & Jois Narasipura, O. S. (2020). Improved image super-resolution using enhanced generative adversarial network: A comparative study. Advances in Intelligent Systems and Computing, 1159, 201–213. https://doi.org/10.1007/978-981-33-4582-9_15
Prastika, D. (2021). Teknik mendeteksi citra CCTV yang bernoise dengan alur garis menggunakan metode Speed-Up Robust Future (SURF). Jurnal Teknologi Informasi, 15(1), 33–40.
Rakotonirina, N., & Rasoanaivo, A. (2020). ESRGAN+: Further improving enhanced super-resolution generative adversarial network. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). https://doi.org/10.1109/ICASSP40776.2020.9054071
Renieblas, G. P., Nogues, A. T., González, A. M., Gómez-Leon, N., & Del Castillo, E. G. (2017). Structural similarity index family for image quality assessment in radiological images. Journal of Medical Imaging, 4(3), 035501. https://doi.org/10.1117/1.JMI.4.3.035501
Ritchie, K. L., White, D., Kramer, R. S. S., Noyes, E., Jenkins, R., & Burton, A. M. (2018). Enhancing CCTV: Averages improve face identification from poor‐quality images. Applied Cognitive Psychology, 32(3), 263–275. https://doi.org/10.1002/acp.3449
Salguero-Cruz, A., Carmona, P., & García-Osorio, C. (2022). Proposal of a comparative framework for face super-resolution algorithms in forensics. In Advances in Computational Intelligence (pp. 403–415). https://doi.org/10.1007/978-3-031-04881-4_36
Sara, A., Altun, G., Şahin, E., & Talu, M. F. (2024). Image-to-image translation with CNN-based perceptual similarity metrics. Bilgisayar Bilimleri Dergisi, 8(1), 10–20. https://doi.org/10.53070/bbd.1429596
Satiro, J., Nasrollahi, K., Correia, P. L., & Moeslund, T. B. (2015). Super-resolution of facial images in forensic scenarios. Proceedings of the International Conference on Image Processing (ICIP). https://doi.org/10.1109/IPTA.2015.7367096
Schlosser, H. (2022). Enhancing image resolution with generative adversarial networks. Proceedings of the 2022 7th International Conference on Computer Science and Engineering (UBMK). https://doi.org/10.1109/ubmk55850.2022.9919520
Seckiner, D., Mallett, X., Roux, C., Meuwly, D., & Maynard, P. (2018). Forensic image analysis: CCTV distortion and artifacts. Forensic Science International, 289, 201–212. https://doi.org/10.1016/J.FORSCIINT.2018.01.024
Senan, M. F. E., Abdullah, S. N. H. S., Kharudin, W. M., & Saupi, N. A. M. (2017). CCTV quality assessment for forensics facial recognition analysis. Proceedings of the International Conference on Cloud Computing. https://doi.org/10.1109/CONFLUENCE.2017.7943232
Tanchenko, A. (2014). Visual-PSNR measure of image quality. Journal of Visual Communication and Image Representation, 25(5), 874–881. https://doi.org/10.1016/J.JVCIR.2014.01.008
Vinay, A., Lokesh, A., Kamath, V. R., Murty, K. N. B., & Natarajan, S. (2021). Enhancement of degraded CCTV footage for forensic analysis. In Advances in Intelligent Systems and Computing, 1166, 541–550. https://doi.org/10.1007/978-981-15-5113-0_50
Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., & Loy, C. C. (2018). ESRGAN: Enhanced super-resolution generative adversarial networks. In Proceedings of the European Conference on Computer Vision (ECCV). https://doi.org/10.1007/978-3-030-11021-5_5
White, D., Norell, K., Phillips, P. J., & O’Toole, A. J. (2017). Human factors in forensic face identification. In Handbook of Biometric Anti-Spoofing (pp. 225–240). https://doi.org/10.1007/978-3-319-50673-9_9
Wu, Y.-L., & Chang, C.-J. (2016). Surveillance of public space: CCTV, privacy and sense of safety. Global Journal for Research Analysis, 5(4), 12–15. https://doi.org/10.15373/22778160/APRIL2016/65
Zain, L. A., & Anwar, N. (2022). Analisis forensik citra CCTV menggunakan bilinear interpolasi dan adaptive median filter. Jurnal Sistem Informasi dan Teknik Informatika, 10(2), 45–53. http://dx.doi.org/10.12928/jstie.v10i2.22471
Zhang, T. (2019). Research and improvement of single image super-resolution based on generative adversarial network. Journal of Physics: Conference Series, 1237(3), 032046. https://doi.org/10.1088/1742-6596/1237/3/032046
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 International Journal of Multilingual Education and Applied Linguistics
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
