PSO-WESRGAN : a novel document image super resolution

• Autorzy: Kezzoula Zakia , Gaceb Djamel

Identyfikatory

DOI

10.7494/csci.2025.26.4.6482

• Języki publikacji: EN

Abstrakty

EN

One of the major challenges of document images that can hinder readability and the analysis of information is low resolution; this is typically caused bylow-pixel density scanning or excessive compression to save storage space. This results in a loss of fine detail in images, making it difficult to detect critical information. To solve these problems, super-resolution techniques are used. These techniques improve image quality by increasing the resolution while maintaining the fine detail. PSO-WESRGAN is an innovative method that combines wavelet processing, deep-transfer learning, and particle swarm optimization (PSO). Wavelet processing analyzes image detail at diverse scales and orientations, while transfer-based deep-learning advantages pretrained models onvast image data sets. By integrating PSO, the efficiency of the method is enhanced through the optimal exploration of the solution space to identify the best parameters for the super-resolution model. The experimental results show the effectiveness of this method and open up prospects for future improvements in the super-resolution of document images.

Słowa kluczowe

EN

document image; super-resolution; transfer deep learning; particle swarm optimization; wavelet transform

• Wydawca: Wydawnictwa AGH
• Czasopismo: Computer Science
• Rocznik: 2025
• Tom: T. 26 (4)
• Strony: 5--31
• Opis fizyczny: Bibliogr. 48 poz., rys., tab., wykr.

Twórcy

autor

Kezzoula Zakia

• University M’Hamed Bougara of Boumerdes, LIMOSE Laboratory, Algeria

autor

Gaceb Djamel

• University M’Hamed Bougara of Boumerdes, LIMOSE Laboratory, Algeria

Bibliografia

• [1] Akima H.: A method of bivariate interpolation and smooth surface fitting forirregularly distributed data points, ACM Transactions on Mathematical Software (TOMS), vol. 4(2), pp. 148–159, 1978. doi: 10.1145/355780.355786.
• [2] Behjati P., Rodriguez P., Fernandez C., Hupont I., Mehri A., Gonzalez J.: Singleimage super-resolution based on directional variance attention network, Pattern Recognition, vol. 133, 108997, 2023. doi: 10.1016/j.patcog.2022.108997.
• [3] Chang Y., Chen G., Chen J.: Pixel-Wise Attention Residual Network for Super-Resolution of Optical Remote Sensing Images, Remote Sensing, vol. 15, 12, 2023.doi: 10.3390/rs15123139.
• [4] Chen X., Wang X., Zhou J., Qiao Y., Dong C.: Activating more pixels in image super-resolution transformer. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22367–22377, 2023. doi: 10.1109/cvpr52729.2023.02142.
• [5] Deng L., Zhang Y., Xin Y., al.: Meta-Learning Multi-Scale Radiology MedicalImage Super-Resolution, Computers, Materials and Continua, vol. 75, 2, 2023.doi: 10.32604/cmc.2023.036642.
• [6] Dohyun K., Joongheon K., Junseok K.a.: Depth-controllable very deep super-resolution network. In: International Joint Conference on Neural Networks (IJCNN), pp. 1–8, IEEE, 2019. doi: 10.1109/ijcnn.2019.8851874.
• [7] Dong C.C., He L.K., X. T.: Learning a Deep Convolutional Network for Image Super-Resolution. In: European Conference on Computer Vision (ECCV), 2014. doi: 10.1007/978-3-319-10593-213.
• [8] Dwarikanath M., Behzad B. R.: Image super-resolution using progressive generative adversarial networks for medical image analysis, Computerized Medical Imaging and Graphics, vol. 71, pp. 30–39, 2019. doi: 10.1016 /j.compmedimag.2018.10.005.
• [9] El-shafai W.M., Ehab M., Zeghid M., al.: Hybrid Single Image Super-Resolution Algorithm for Medical Images, Computers, Materials and Continua, vol. 72, p. 3,2022. doi: 10.32604/cmc.2022.028364.
• [10] Fan Q., Wu C., Hu S., Wu X., Wang X., Hu J.: Efficient Image Super-Resolution via Symmetric Visual Attention Network. In: 2024 International Joint Conference on Neural Networks (IJCNN), 2024. doi: 10.1109/ijcnn60899.2024.10650362.
• [11] Gallivan K., Grimme G., Van Dooren P.: Arational Lanczos algorithm formodel reduction, Numerical Algorithms, vol. 12, pp. 33–63, 1996. doi: 10.1007/bf02141740.
• [12] Getreuer P.: Contour stencils for edge- adaptive image interpolation. In: M. Rabbani, R.L. Stevenson (eds.), Visual Communications and Image Processing 2009, vol. 7257, 2009. doi: 10.1117/12.806014.
• [13] Getreuer P.: Image interpolation with contour stencils, Image Processing OnLine, vol. 1, pp. 70–82, 2011. doi: 10.5201/ipol.2011.giics.
• [14] Gordon W.J., Riesenfeld R.F.: B-spline curves and surfaces. In: R.E. Barnhill, R.F. Riesenfeld (eds.), Computer Aided Geometric Design, pp. 95–126, Academic Press, 1974. doi: 10.1016/b978-0-12-079050-0.50011-4.
• [15] Grandke T.: Interpolation algorithms for discrete Fourier transforms of weighted signals, IEEE Transactions on Instrumentation and Measurement, vol. 32(2), pp. 350–355, 1983. doi: 10.1109/tim.1983.4315077.
• [16] Hall C.A.: Bicubic interpolation over triangles, Indiana University Mathematics Journal, vol. 19(1), pp. 1–11, 197. doi: 10.1512/iumj.1970.19.19001.
• [17] He Z., Chen D., Cao Y., Yang J., Cao Y., Li X., Tang S., et al.: Single image super-resolution based on progressive fusion of orientation-aware features, Pattern Recognition, vol. 133, 109038, 2023. doi: 10.1016/j.patcog.2022.109038.
• [18] Hsu C.C., Lee C.M., Chou Y.S.: DRCT: Saving Image Super-Resolution away from Information Bottleneck. In: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 6133–6142, 2024.doi: 10.1109/cvprw63382.2024.00618.
• [19] Kezzoula Z., Gaceb D., Akli Z., Kahouli A., Titoun A., Touazi F.: Bi-ESRGAN: A New Approach of Document Image Super-Resolution Based on Dual Deep Transfer Learning. In: International Conference on Artificial Intelligence: Theories and Applications, pp. 110–122, Springer, 2022. doi: 10.1007/978- 3- 031-28540-09.
• [20] Lai W.S., Huang J.B., Ahuja N., Yang M.H.: Fast and accurate image super-resolution with deep laplacian pyramid networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41(11), pp. 2599–2613, 2018. doi: 10.1109/tpami.2018.2865304.
• [21] Ledig C., Theis L., Huszar F., Caballero J., Cunningham A., Acosta A., Aitken A., et al.: Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. In: 2017 IEEE Conference on Computer Visionand Pattern Recognition (CVPR), pp. 105–114, IEEE, 2017.doi: 10.1109/cvpr.2017.19.
• [22] Liang J., Cao J., Sun G., Zhang K., Van Gool L., Timofte R.: Swinir : Image restoration using swin transformer. In: Proceedings of the IEEE/CVF international conference on computer vision, pp. 1833–1844, 2021. doi: 10.1109/iccvw54120.2021.00210.
• [23] Lim B., Son S., Kim H., Nah S., Lee K.M.: Enhanced Deep Residual Networksfor Single Image Super-Resolution. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1132–1140, 2017.doi: 10.1109/cvprw.2017.151.
• [24] Luo J., Han L., Gao X., Liu X., Wang W.: SR-FEINR: Continuous Remote Sensing Image Super-Resolution Using Feature-Enhanced Implicit Neural Representation, Sensors, vol. 23(7), 3573, 2023. doi: 10.3390/s23073573.
• [25] Mao Y., Zhang N., Wang Q., Bai B., Bai W., Fang H., Liu P., Li M., Yan S.: Multi-level Dispersion Residual Network for Efficient Image Super-Resolution. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Work-shops (CVPRW), pp. 1660–1669, 2023. doi: 10.1109/CVPRW59228.2023.00167.
• [26] Masayuki O.: Explicit interpolation formulas for the Bell triangle, Computer Methods in Applied Mechanics and Engineering, vol. 117(3–4), pp. 411–421, 1994.doi: 10.1016/0045-7825(94)90126-0.
• [27] Mitchell D.P., Netravali A.N.: Reconstruction filters in computer-graphics, ACM Siggraph Computer Graphics, vol. 22(4), pp. 221–228, 1988.doi: 10.1145/378456.378514.
• [28] Narasimhan S.V., Basumallick N., Veena S.: Introduction to Wavelet Transform: A Signal Processing Approach, Alpha Science International, Ltd, 2011.
• [29] Olsson A.E.: Particle Swarm Optimization: Theory, Techniques and Applications, 2011.
• [30] Othman G., Zeebaree D.Q.: The applications of discrete wavelet transform in image processing: A review, Journal of Soft Computing and Data Mining, vol. 1(2),pp. 31–43, 2020.
• [31] Ray A., Kumar G., Kolekar M.H.: CFAT: Unleashing Triangular Windows for Image Super-resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 26120–26129, 2024. doi: 10.1109/cvpr52733.2024.02468.
• [32] Reyes-Saldana E., Rivera M.: EXTRACTER: Efficient Texture Matching with Attention and Gradient Enhancing for Large Scale Image Super Resolution, 2023.doi: 10.2139/ssrn.5347487.
• [33] Salvetti F., al.: Multi-Image Super Resolution of Remotely Sensed Images Using Residual Attention Deep Neural Networks, Remote Sensing, vol. 12, 14, 2020.doi: 10.3390/rs12142207.
• [34] Schumer M.: Interpolation of a Gaussian-Markov process (Corresp.), IEEE Transactions on Information Theory, vol. 16(1), pp. 75–77, 1970. doi: 10.1109/tit.1970.1054397.
• [35] Shi Y.: Particle swarm optimization, IEEE Connections, vol. 2(1), pp. 8–13,2004.
• [36] Smith P.R.: Bilinear interpolation of digital images, Ultramicroscopy, vol. 6(2), pp. 201–204, 1981. doi: 10.1016/0304-3991(81)90061-9.
• [37] Sun L., Dong J., Tang J., Pan J.: Spatially-adaptive feature modulation for efficient image super-resolution. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 13190–13199, 2023. doi: 10.1109/iccv51070.2023.01213.
• [38] Tao Y., Muller J.P.: Super-Resolution Restoration of Spaceborne Ultra-High-Resolution Images Using the UCL OpTiGAN System, Remote Sensing, vol. 13,12, 2021. doi: 10.3390/rs13122269.
• [39] Tian C., Zhang X., Zhang Q., Yang M., Ju Z.: Image super-resolution viadynamic network, CAAI Transactions on Intelligence Technology, vol. 9(4),pp. 837–849, 2024. doi: 10.1049/cit2.12297.
• [40] Tran D.P., Hung D.D., Kim D.: Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution, arXiv preprintarXiv:240716232, 2024.
• [41] Tsai R.Y., Huang T.S.: Multiframe image restoration and registration. In: T.S. Huang (ed.), Advances in Computer Vision and Image Processing, vol. 1,pp. 317–339, JAI Press, 1984.
• [42] Urbina Ortega C., Quevedo Gutierrez E., Quintana L., Ortega S., Fabelo H., Santos Falcon L., Marrero Callico G.: Towards Real-Time Hyperspectral Multi-Image Super-Resolution Reconstruction Applied to Histological Samples, Sensors, vol. 23, 4, 2023. doi: 10.3390/s23041863.
• [43] Walker B.: Particle Swarm Optimization (PSO), Advances in Research and Applications, 2017.
• [44] Wang X., Yu K., Wu S., Gu J., Liu Y., Dong C., Qiao Y., Loy C.C.: ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks. In: L. Leal-Taixe,S. Roth (eds.), Computer Vision – ECCV 2018 Workshops, pp. 63–79, Springer, Cham, 2019. doi: 10.1007/978-3-030-11021-55.
• [45] Wang Z., Cun X., Bao J., Zhou W., Liu J., Li H.: Uformer: A General U-Shaped Transformer for Image Restoration. In: 2022 IEEE/CVF Conferenceon Computer Vision and Pattern Recognition (CVPR), pp. 17662–17672, 2022. doi: 10.1109/CVPR52688.2022.01716.
• [46] Zhang K., Zuo W., Zhang L.: Deep Plug-And-Play Super-Resolution for Arbitrary Blur Kernels. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1671–1681, 2019. doi: 10.1109/cvpr.2019.00177.
• [47] Zhang Y., Li K., Li K., Wang L., Zhong B., Fu Y.: Image Super-Resolution UsingVery Deep Residual Channel Attention Networks. In: V. Ferrari, M. Hebert,C. Sminchisescu, Y. Weiss (eds.), Computer Vision – ECCV 2018, pp. 286–301, Springer, Cham, 2018. doi: 10.1007/978-3-030-01234-218.
• [48] Zhang Y., Tian Y., Kong Y., Zhong B., Fu Y.: Residual Dense Network for Image Super-Resolution. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2472–2481, IEEE, 2018. doi: 10.1109/cvpr.2018.00262.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).