Loading Now
IJCT Policy Low Cost Publication Publication Guidelines

Feature Map Attention Mechanism for Single Image Super-Resolution

International Journal of Computer Techniques (IJCT) – Volume 12 Issue 2, April 2025

Akhila Manchikatla, Gadey Rakesh Kumar, Gugulothu Akhil
Computer Science And Engineering
Institute Of Aeronautical Engineering
Hyderabad, India.
Email: manchikatlakhila11@gmail.com, gadeyrakesh05@gmail.com, akhilgugulothu1@gmail.com

Ala Harika
Computer Science And Engineering
Institute Of Aeronautical Engineering
Hyderabad, India.
Email: alaharika@iare.ac.in

Abstract

Using an attention mechanism with feature maps, the paper proposes an image super-resolution reconstruction method to address the challenge of treating low- and high-frequency components equally in existing methods. The model consists of three main modules: feature extraction, information extraction, and reconstruction. The feature extraction block captures key details from low-resolution images, while the information extraction block, enhanced by an attention mechanism, refines these features by adapting to channel characteristics. Experimental results demonstrate that this approach improves image quality, as evidenced by higher PSNR and SSIM scores, and shows effectiveness across the used dataset. Proposed algorithm gives output images with less sharpness, so there is an additional algorithm added for sharpness improvement as well as contrast enhancement to obtain final images with high resolution and enhanced quality. OpenCV library is used for improving the quality of an image.

Keywords

attention mechanism, feature map, super resolution, image enhancement, OpenCV

References

  1. Zhang L, Wu X (2006) An edge-guided image interpolation algorithm via directional filtering and data fusion. IEEE Trans Image Process 15(8):2226–2238
  2. Chen YT, Tao JJ, Liu LW, Xiong J, Xia RL, Xie JB, Zhang Q, Yang K (2020) Research of improving semantic image segmentation based on a feature fusion model. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-020-02066-z
  3. Chen YT, Wang J, Liu SJ, Chen X, Xiong J, Xie JB, Yang K (2019) The multi-scale fast correlation filtering tracking algorithm based on a features fusion model. Concurrency Computat Pract Exper. https://doi.org/10.1002/cpe.5533
  4. Yang J, Wright J, Huang TS, Yu L (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873
  5. Timofte R, De Smet V, Van Gool L (2013) Anchored neighborhood regression for fast example-based super-resolution. Paper presented at: Proceedings of the 2013 IEEE conference on computer vision (ICCV), Sydney, Australia, pp 1920–1927
  6. Dong C, Loy CC, He KM, Tang XO (2014) Learning a deep convolutional network for image super-resolution. Paper presented at: Proceedings of the European conference on computer vision (ECCV), Zurich, Switzerland, pp 184–199
  7. Kim J, Kwon Lee J, Mu Lee K (2016) Accurate image superresolution using very deep convolutional networks. Paper presented at: Proceedings of the 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, pp 1646–1654
  8. He KM, Zhang XY, Ren SQ, Sun J (2016) Deep residual learning for image recognition. Paper presented at: Proceedings of the 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, pp 770–778
  9. Chen YT, Xiong J, Xu WH, Zuo JW (2019) A novel online incremental and decremental learning algorithm based on variable support vector machine. Cluster Comput 22(3):7435–7445
  10. Lim B, Son S, Kim H, Nah S, Lee KM (2017) Enhanced deep residual networks for single image super-resolution. Paper presented at: Proceedings of the 2017 IEEE conference on computer vision and pattern recognition workshops (CVPR workshops), Honolulu, pp 1132–1140
  11. Tai Y, Yang J, Liu XM (2017) Image super-resolution via deep recursive residual network. Paper presented at: Proceedings of the 2017 IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, pp 2790–2798
  12. Chen YT, Zhang HP, Liu LW, Tao JJ, Zhang Q, Yang K, Xia RL, Xie JB (2020) The image inpainting algorithm of texture decomposition and local variation minimization. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-020-02778-2
  13. Zhang H, Wang XM, Gao XB (2018) Fast and accurate single image super-resolution via information distillation network. Paper presented at: Proceedings of the 2018 IEEE conference on computer vision and pattern recognition (CVPR), Salt Lake City, pp 723–731
  14. Sakai Y, Lu HM, Tan J-K, Kim H (2019) Recognition of surrounding environment from electric wheelchair videos based on modified YOLOv2. Futur Gener Comput Syst 92:157–161
  15. Memisevic R, Konda KR, Krueger D (2015) Zero-bias autoencoders and the benefits of co-adapting features. Paper presented at: Proceedings of the 2015 International Conference on Learning Representations (ICLR), San Diego, CA, USA arXiv:1402.3337
FAM image resolution IEEE-Download

Share this content:

Tag

IJCT Latest News

Post Comment

Reviewer Board