Comparative Analysis of Integrated Learning Based Methods for Image ‎Super-Resolution

  • Authors

    • Kavya T. . Research Scholar M Department of P.G Studies and Research in ‎Computer Science, Kuvempu University, ‎Shivamogga, Karnataka, India
    • Dr. Yogish Naik G. R Associate Professor, Department of P.G ‎Studies and Research in Computer Science,‎ Kuvempu University, Shivamogga, Karnataka, India
    https://doi.org/10.14419/vv8ve405

    Received date: June 23, 2025

    Accepted date: July 28, 2025

    Published date: August 2, 2025

  • Sparse Representation; ASDS_AR; K_SVD; SRGAN

  • Abstract

    Image super-resolution (SR) is a fundamental problem in computer vision aimed at ‎reconstructing high-resolution (HR) images from low-resolution (LR) inputs. Various methods have ‎been proposed to solve this problem, ranging from traditional signal processing techniques to modern ‎deep learning-based approaches. Two prominent methods in SR are Sparse Representation (SR) and ‎the ASDS_AR (Attention-based Super-Resolution with Discriminative Spatial Attention Residuals) ‎technique. Sparse representation, typically used with dictionary learning and sparse coding, models ‎images as sparse combinations of learned atoms from a dictionary, allowing for the recovery of fine ‎details. On the other hand, the ASDS_AR method leverages deep learning, particularly attention ‎mechanisms and residual learning, to focus on important spatial regions and enhance the image ‎resolution. This paper presents a comparative study of these two approaches in terms of their ‎performance, computational efficiency, and ability to preserve fine image details. Through qualitative ‎and quantitative evaluation on several benchmark datasets, we analyze the strengths and weaknesses ‎of each method in terms of image quality, PSNR, SSIM, and perceptual metrics‎.

  • References

    1. . Elad, M., & Aharon, M. (2016). Image Denoising via Sparse and Redundant Representations Over Learned Dictionaries. IEEE Transactions on Im-age Processing, 15(12), 3736-3745. https://doi.org/10.1109/TIP.2006.881969.
    2. . Ledig, C., Theis, L., Huszár, F., et al. (2017). Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. IEEE Con-ference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR.2017.19.
    3. . Dong, C., Loy, C. C., He, K., & Tang, X. (2016). Image Super-Resolution Using Deep Convolutional Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/TPAMI.2015.2439281.
    4. . Zhang, X., & Zhai, Y. (2020). ASDS_AR: Attention-based Super-resolution with Discriminative Spatial Attention Residuals. Journal of Machine Learning Research.
    5. . Mohan K, Chandrasekhar P, Jilani SAK. Object Face Liveness Detection with Combined HOGlocal Phase Quantization using Fuzzy based SVM Classifier. Indian Journal of Science and Technology. 2017;10(3):1–10. Available from: https://doi.org/10.17485/ijst/2017/v10i3/109035.
    6. . Kumaravel S, Sundar KJA, Vaithiyanathan V. Super Resolution Image Reconstruction for Bone Images. Indian Journal of Science and Technology. 2019;12(26):1–6. https://doi.org/10.17485/ijst/2019/v12i26/117915.
    7. . Saffari V, Ghazimoradi A, Alirezanejad M. Effect of Laplacian of Gaussian Filter on Watermark Retrieval in Spatial domain Watermarking. Indian Journal of Science and Technology. 2015;8(33):1–4. Available from: https://doi.org/10.17485/ijst/2015/v8i1/71226.
    8. . Fairag F, Chen K, Brito-Loeza C, Ahmad S. A two-level method for image denoising and image deblurring models using mean curvature regulari-zation. International Journal of Computer Mathematics. 2021; p. 1–21. Available from: https://doi.org/10.1080/00207160.2021.1929939.
    9. . Yu X, Xie W. Single Image Blind Deblurring Based on Salient Edge-Structures and Elastic-Net Regularization. Journal of Mathematical Imaging and Vision. 2020;62(8):1049–1061. Available from: https://doi.org/10.1007/s10851-020-00949-6.
    10. . Zhao C, Wang Y, Jiao H. Lp-Norm-Baesd Sparse Regularization Model for Liscence Plate Deblurring. IEEE Access. 2020; 8:22072–22081. https://doi.org/10.1109/ACCESS.2020.2969675.
    11. . er´ emy Anger J, Facciolo G, Delbracio M. Blind image deblurring using the lo gradient prior, Image Process. On Line. 2019; 9:124–142. Available from: https://doi.org/10.5201/ipol.2019.243.
    12. . Xu Z, Chen H, Li Z. Blind image deblurring using group sparse representation. Digital Signal Processing. 2020;102(1-8):1–8. Available from:. https://doi.org/10.1016/j.dsp.2020.102736.
    13. . Wen-Ze S, Yuan-Yuan L, Lu-Yue Y. DeblurGAN+: Revisiting blind motion deblurring using conditional adversarial networks. Signal Pro-cessing.2020;168:1–10. Available from:. https://doi.org/10.1016/j.sigpro.2019.107338.
    14. . Hsieh PW, Shao PC. Blind image deblurring based on the sparsity of patch minimum information. Pattern Recognition. 2021;109. Available from:. https://doi.org/10.1016/j.patcog.2020.107597.

  • Downloads

  • How to Cite

    M, K. T. . R. S., & R, D. Y. N. G. . (2025). Comparative Analysis of Integrated Learning Based Methods for Image ‎Super-Resolution. International Journal of Basic and Applied Sciences, 14(4), 17-23. https://doi.org/10.14419/vv8ve405