Reconstruction of Low-Resolution Facial Images Using Improvements to the FSRCNN Model with Parallel Feature Extraction Layers and Residual Connections
DOI:
https://doi.org/10.30595/jrst.v9i2.24237Keywords:
FSRCNN, Image Reconstruction, Super-Resolution, Parallel Feature Extraction, Residual ConnectionAbstract
Enhancing the quality of reconstructing low-resolution facial images poses a significant challenge in various applications, particularly in CCTV-based surveillance. This study develops a Fast Super-Resolution Convolutional Neural Network (FSRCNN) model with the addition of parallel feature extraction layers and residual connections from these layers to the expanding layer to improve the reconstruction quality of faces from low resolution. The proposed model is tested using two datasets: CelebA and CCTV footage. The tests are conducted for two reconstruction scales, namely from LR to HR and from LR to intermediate. The results demonstrate that the proposed model consistently outperforms the standard FSRCNN. In the LR to HR reconstruction, the proposed model achieves an average PSNR improvement of 1.24 dB and an SSIM increase of 0.0584 on the CelebA dataset. For the CCTV dataset, an average PSNR enhancement of 0.52 dB and an SSIM improvement of 0.025 are attained. While this model significantly enhances image quality, several limitations were identified regarding performance on more varied CCTV images and the higher complexity of the model.
References
Ahn, S., & Kang, S.-J. (2021). Deep Learning-based Real-Time Super-Resolution Architecture Design. Journal of Broadcast Engineering, 26(2), 167–174. https://doi.org/10.5909/JBE.2021.26.2.167
Bai, Y., Berezovsky, V., & Popov, V. (2020). Super Resolution for Digital Rock Core Images via FSRCNN. Proceedings of the 2020 4th High Performance Computing and Cluster Technologies Conference & 2020 3rd International Conference on Big Data and Artificial Intelligence, 78–81. https://doi.org/10.1145/3409501.3409528
Bulat, A., Yang, J., & Tzimiropoulos, G. (2018). To learn image super-resolution, use a gan to learn how to do image degradation first. Proceedings of the European Conference on Computer Vision (ECCV), 185–200. https://doi.org/10.1007/978-3-030-01231-1_12
Cheng, Z., Zhu, X., & Gong, S. (2020). Face re-identification challenge: Are face recognition models good enough? Pattern Recognition, 107, 107422. https://doi.org/https://doi.org/10.1016/j.patcog.2020.107422
Das, S. K., Roy, P., & Mishra, A. K. (2022). DFU_SPNet: A stacked parallel convolution layers based CNN to improve Diabetic Foot Ulcer classification. ICT Express, 8(2), 271–275. https://doi.org/https://doi.org/10.1016/j.icte.2021.08.022
Dong, C., Loy, C. C., & Tang, X. (2016). Accelerating the super-resolution convolutional neural network. Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14, 391–407. https://doi.org/10.1007/978-3-319-46475-6_25
Hou, J., Si, Y., & Yu, X. (2020). A novel and effective image super-resolution reconstruction technique via fast global and local residual learning model. Applied Sciences, 10(5), 1856. https://doi.org/10.3390/app10051856
Ivanov, N. S., Arzhskov, A. V, & Ivanenko, V. G. (2020). Combining Deep Learning and Super-Resolution Algorithms for Deep Fake Detection. 2020 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), 326–328. https://doi.org/10.1109/EIConRus49466.2020.9039498
Khachatryan, T., Galstyan, D., & Harutyunyan, E. (2023). A Comprehensive Approach for Enhancing Deep Learning Datasets Quality Using Combined SSIM Algorithm and FSRCNN. 2023 IEEE East-West Design & Test Symposium (EWDTS), 1–4. https://doi.org/10.1109/EWDTS59469.2023.10297040
Li, Z., Liu, Y., Chen, X., Cai, H., Gu, J., Qiao, Y., & Dong, C. (2022). Blueprint Separable Residual Network for Efficient Image Super-Resolution. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 832–842. https://doi.org/10.1109/CVPRW56347.2022.00099
Niu, Y., Weng, H., Lin, J., & Liu, G. (2020). Single Image Super-Resolution: From Discrete to Continuous Scale Without Retraining. IEEE Access, 8, 32121–32136. https://doi.org/10.1109/ACCESS.2020.2973283
Passarella, L. S., Mahajan, S., Pal, A., & Norman, M. R. (2022). Reconstructing high resolution ESM data through a novel fast super resolution convolutional neural network (FSRCNN). Geophysical Research Letters, 49(4), e2021GL097571. https://doi.org/10.1029/2021GL097571
Qiu, D., Zheng, L., Zhu, J., & Huang, D. (2021). Multiple improved residual networks for medical image super-resolution. Future Generation Computer Systems, 116, 200–208. https://doi.org/https://doi.org/10.1016/j.future.2020.11.001
Satyagama, P., & Widyantoro, D. H. (2020). Low-Resolution Face Recognition System Using Siamese Network. 2020 7th International Conference on Advance Informatics: Concepts, Theory and Applications (ICAICTA), 1–6. https://doi.org/10.1109/ICAICTA49861.2020.9428885
Wang, B., Zou, Y., Zhang, L., Hu, Y., Yan, H., Zuo, C., & Chen, Q. (2021). Low-Light-Level Image Super-Resolution Reconstruction Based on a Multi-Scale Features Extraction Network. Photonics, 8(8). https://doi.org/10.3390/photonics8080321
Wu, H., Bezold, G., Günther, M., Boult, T., King, M. C., & Bowyer, K. W. (2023). Consistency and Accuracy of CelebA Attribute Values. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 3258–3266. https://doi.org/10.1109/CVPRW59228.2023.00328
Zhang, F., Cai, N., Cen, G., Li, F., Wang, H., & Chen, X. (2018). Image super-resolution via a novel cascaded convolutional neural network framework. Signal Processing: Image Communication, 63, 9–18. https://doi.org/https://doi.org/10.1016/j.image.2018.01.009
Zhang, J., Liu, M., Wang, X., & Cao, C. (2021). Residual Net Use on FSRCNN for Image Super-Resolution. 2021 40th Chinese Control Conference (CCC), 8077. https://doi.org/10.23919/CCC52363.2021.9550205
Zhang, Y., Yin, Z., Li, Y., Yin, G., Yan, J., Shao, J., & Liu, Z. (2020). CelebA-Spoof: Large-Scale Face Anti-spoofing Dataset with Rich Annotations. In A. Vedaldi, H. Bischof, T. Brox, & J.-M. Frahm (Eds.), Computer Vision -- ECCV 2020 (pp. 70–85). Springer International Publishing. https://doi.org/10.1007/978-3-030-58610-2_5
Zhao, Z., Li, Q., Zhang, Z., Cummins, N., Wang, H., Tao, J., & Schuller, B. W. (2021). Combining a parallel 2D CNN with a self-attention Dilated Residual Network for CTC-based discrete speech emotion recognition. Neural Networks, 141, 52–60. https://doi.org/https://doi.org/10.1016/j.neunet.2021.03.013
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Tommy, Rosyidah Siregar, Edy Rahman Syahputra
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access)
JRST (Jurnal Riset Sains dan Teknologi) is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
