Enhancing Facial Image Restoration Using CNN for Blur Severity Classification and U-Net for Deblurring
DOI:
https://doi.org/10.25139/inform.v10i2.9542Keywords:
Blur severity classification, Image deblurring, Convolutional Neural Network, U-NetAbstract
Blurring facial images can significantly degrade the performance of face recognition and video surveillance applications. Therefore, an effective image restoration method is essential to address this issue. However, existing methods struggle with varying levels of blur severity, limiting their effectiveness. This study proposes a facial image restoration approach that integrates blur severity classification using a Convolutional Neural Network (CNN) with a U-Net-based deblurring model to overcome these challenges. This method ensures that each blurred image is processed using the most suiTable deblurring model, optimizing the restoration process. The dataset used in this study is Flickr-Faces-HQ (FFHQ), to which a Gaussian blur is applied and categorized into five levels: very low, low, medium, high, and very high. They employ the Peak Signal-to-Noise Ratio (PSNR) and the Structural Similarity Index Measure (SSIM) as quantitative metrics to evaluate the model's performance. Experimental results show that the proposed method consistently outperforms fixed kernel size and multi-kernel size deblurring approaches across all blur severities. Specifically, our method achieves a PSNR of 40.001 dB for very low blur severity and an SSIM of 0.990. For low severity, it attains a PSNR of 31.104 dB and an SSIM of 0.946. For medium severity, the results are 27.995 dB (PSNR) and 0.874 (SSIM). At high severity, our model achieves a PSNR of 28.896 dB and an SSIM of 0.855. Finally, for very high severity, the PSNR drops to 26.566 dB, with an SSIM of 0.812. These results demonstrate the effectiveness of the proposed method in enhancing image clarity across different blur levels while preserving facial details. This research contributes to the development of more adaptive and efficient image restoration techniques, particularly for applications that require high-quality facial images, such as face recognition and video surveillance.
References
Y. Kim, H. Kwon, and H. Ko, "Facial image deblurring network for robust illuminance adaptation and key structure restoration," Eng. Appl. Artif. Intell., vol. 133, no. PA, p. 107959, 2024, doi: 10.1016/j.engappai.2024.107959.
S. H. Jung, T. Bok Lee, and Y. S. Heo, "Deep Feature Prior Guided Face Deblurring," Proc. - 2022 IEEE/CVF Winter Conf. Appl. Comput. Vision, WACV 2022, pp. 884–893, 2022, doi: 10.1109/WACV51458.2022.00096.
S. S. Beulah Benslet and P. Parameswari, "Enhancement of Criminal Facial Image Using Multistage Progressive V-Net for Facial Recognition by Pixel Restoration," ICST Trans. Scalable Inf. Syst., vol. 11, no. 3, 2024, doi: 10.4108/eetsis.3980.
B. Wang, F. Xu, and Q. Zheng, "A survey on facial image deblurring," Comput. Vis. Media, vol. 10, no. 1, pp. 3–25, 2023, doi: 10.1007/s41095-023-0336-6.
Z. Yu, "Image deblurring: comparison and analysis," J. Phys. Conf. Ser., vol. 2634, no. 1, p. 012034, Nov. 2023, doi: 10.1088/1742-6596/2634/1/012034.
A. J. Ajwad and S. Tahmed Salim Rafid, "Enhancing Facial Image Clarity: Deblurring Gaussian blur with UNET++ Architecture," in 2023 26th International Conference on Computer and Information Technology (ICCIT), IEEE, Dec. 2023, pp. 1–4. doi: 10.1109/ICCIT60459.2023.10441021.
Q. Qi, J. Guo, C. Li, and L. Xiao, "Blind face images deblurring with enhancement," Multimed. Tools Appl., vol. 80, no. 2, pp. 2975–2995, 2021, doi: 10.1007/s11042-020-09460-x.
C. Cai, H. Meng, and Q. Zhu, "Blind deconvolution for image deblurring based on edge enhancement and noise suppression," IEEE Access, vol. 6, pp. 58710–58718, 2018, doi: 10.1109/ACCESS.2018.2874980.
R. Yasarla, F. Perazzi, and V. M. Patel, "Deblurring Face Images Using Uncertainty Guided Multi-Stream Semantic Networks," IEEE Trans. Image Process., vol. 29, pp. 6251–6263, 2020, doi: 10.1109/TIP.2020.2990354.
Y. Pang, J. Mao, L. He, H. Lin, and Z. Qiang, "An Improved Face Image Restoration Method Based on Denoising Diffusion Probabilistic Models," IEEE Access, vol. 12, no. January, pp. 3581–3596, 2024, doi: 10.1109/ACCESS.2024.3349423.
R. Wang, W. Li, R. Qin, and J. Z. Wu, "Blur image classification based on deep learning," IST 2017 - IEEE Int. Conf. Imaging Syst. Tech. Proc., vol. 2018-Janua, pp. 1–6, 2017, doi: 10.1109/IST.2017.8261503.
R. Wang, W. Li, and L. Zhang, "Blur image identification with ensemble convolution neural networks," Signal Processing, vol. 155, pp. 73–82, 2019, doi: 10.1016/j.sigpro.2018.09.027.
S. Tiwari, "A blur classification approach using deep convolution neural network," Int. J. Inf. Syst. Model. Des., vol. 11, no. 1, pp. 93–111, 2020, doi: 10.4018/IJISMD.2020010106.
M. Tripathi, "Facial image denoising using AutoEncoder and UNET," Herit. Sustain. Dev., vol. 3, no. 2, pp. 89–96, 2021, doi: 10.37868/hsd.v3i2.71.
Z. Lian and H. Wang, "An image deblurring method using improved U-Net model based on multilayer fusion and attention mechanism," Sci. Rep., vol. 13, no. 1, 2023, doi: 10.1038/s41598-023-47768-4.
A. Tharwat, "Classification assessment methods," Appl. Comput. Informatics, vol. 17, no. 1, pp. 168–192, 2018, doi: 10.1016/j.aci.2018.08.003.
A. Horé and D. Ziou, "Image quality metrics: PSNR vs. SSIM," Proc. - Int. Conf. Pattern Recognit., no. March, pp. 2366–2369, 2010, doi: 10.1109/ICPR.2010.579.
D. R. I. M. Setiadi, "PSNR vs SSIM: imperceptibility quality assessment for image steganography," Multimed. Tools Appl., vol. 80, no. 6, pp. 8423–8444, 2021, doi: 10.1007/s11042-020-10035-z.
P. Corke, W. Jachimczyk, and R. Pillat, "Images and Image Processing," Springer Tracts Adv. Robot., vol. 147, pp. 435–491, 2023, doi: 10.1007/978-3-031-07262-8_11.
F. A.-I. A. Putra, A. R. Jatmiko, D. M. Putri, and A. H. Al-Fath, "Vehicle Licence Number Plate Recognition Using Convolution Neural Network for Traffic Violators in Indonesia," Inf. J. Ilm. Bid. Teknol. Inf. dan Komun., vol. 9, no. 2, pp. 181–186, 2024, doi: 10.25139/inform.v9i2.8449.
L. Lisda, K. Kusrini, and D. Ariatmanto, "Classification of Pistachio Nut Using Convolutional Neural Network," Inf. J. Ilm. Bid. Teknol. Inf. dan Komun., vol. 8, no. 1, pp. 71–77, 2023, doi: 10.25139/inform.v8i1.5685.
X. P. Shi, S. Y. Lin, M. L. Yang, C. C. Huang, and J. C. Lee, "Image deblurring by multi-scale modified U-Net using dilated convolution," Sci. Prog., vol. 107, no. 1, pp. 1–24, 2024, doi: 10.1177/00368504241231161.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with Inform: Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi 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 (CC BY-SA 4.0) that allows others to share the work with an acknowledgment 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 acknowledgment 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.
