Convolution Neural Network Approach for Single Image Super Resolution

Lajja Dave; Neha Patel; Nayana Suresh

doi:10.32628/CSEIT2410492

Authors

Lajja Dave Assistant Professor, Sardar Patel College of Engineering, Bakrol, Gujarat, India Author
Neha Patel Teaching Assistant, Sardar Patel College of Engineering, Bakrol, Gujarat, India Author
Nayana Suresh Assistant Professor, Sardar Patel College of Engineering, Bakrol, Gujarat, India Author

DOI:

https://doi.org/10.32628/CSEIT2410492

Keywords:

Super-Resolution, Image Restoration, Convolutional Neural Network, PSNR, Image Processing

Abstract

The goal of Super-Resolution (SR) is to generate a higher-resolution image from lower-resolution input images. High-resolution images offer more pixel density, thus capturing finer details of the original scene. Single Image Super-Resolution (SISR) seeks to restore a high-resolution image from a single low-resolution input, which is a significant challenge in computer vision. This process involves using the low-resolution image as the input and the high-resolution image as the reference, with the SR model producing the predicted high-resolution output. This paper proposes a neural network-based approach utilizing convolutional layers to improve Peak Signal-to-Noise Ratio (PSNR) and reduce processing time compared to traditional methods. The architecture consists of a convolutional layer, a max-pooling layer, and a reconstruction layer.

Downloads

Download data is not yet available.

References

Zhou, Ying, Zheng, Z., & Sun, Q. (2024). Bi-directional projection framework for fast Single Image Super Resolution. Recent Patents on Engineering, 18(9). doi:10.2174/0118722121248802231004053522 DOI: https://doi.org/10.2174/0118722121248802231004053522

Zhou, Yichao, Tang, Z., & Hu, X. (2014). Fast Single Image Super Resolution Reconstruction via Image Separation. Journal of Networks, 9(7). doi:10.4304/jnw.9.7.1811-1818 DOI: https://doi.org/10.4304/jnw.9.7.1811-1818

Nath, A. G., Nair, M. S., & Rajan, J. (2015). Single image super resolution from compressive samples using two level sparsity based reconstruction. Procedia Computer Science, 46, 1643–1652. doi:10.1016/j.procs.2015.02.100 DOI: https://doi.org/10.1016/j.procs.2015.02.100

Purkait, P., & Chanda, B. (2012). Super resolution image reconstruction through Bregman iteration using morphologic regularization. IEEE Transactions on Image Processing: A Publication of the IEEE Signal Processing Society, 21(9), 4029–4039. doi:10.1109/TIP.2012.2201492 DOI: https://doi.org/10.1109/TIP.2012.2201492

Freeman, W. T., Thouis, R., & Jones, E. C. (2002). Example-based superresolution. Computer Graphics and Applications, 22, 56–65. DOI: https://doi.org/10.1109/38.988747

Giaconi, J. C., Allen, C. R., & Steinbach, L. S. (2009). Anterior cruciate ligament graft reconstruction: clinical, technical, and imaging overview. Topics in Magnetic Resonance Imaging: TMRI, 20(3), 129–150. doi:10.1097/RMR.0b013e3181d657a7 DOI: https://doi.org/10.1097/RMR.0b013e3181d657a7

Trimeche, M. (n.d.). Super-Resolution Image Reconstruction Using Non-Linear Filtering.

Nielsen, M. A. (2015). Neural Networks and Deep Learning”. Determination Press.

Farrell, J., Xiao, F., & Kavusi, S. (n.d.). Resolution and light sensitivity trade off.

Goto, T. (2012). Learning-based super-resolution image reconstruction on multicore processor. IEEE Transactions On, 58(3), 941–946. DOI: https://doi.org/10.1109/TCE.2012.6311340

Xiaoqiang, Y., & Yuan, P. (n.d.). Alternatively constrained dictionary.

Liu, D., Wang, Z., & Huang, T. (n.d.). Efficient Image and Video SuperResolution Using Deep Convolutional Neural Networks.

Liu, C., Shum, H.-Y., & Freeman, W. T. (2007). Face hallucination: Theory and practice. International Journal of Computer Vision, 75(1), 115–134. doi:10.1007/s11263-006-0029-5 DOI: https://doi.org/10.1007/s11263-006-0029-5

Naval Criminal Investigative Services (NCIS)” Ikena Forensic video enhancement. (n.d.).

No title. (n.d.). Retrieved 19 September 2024, from https://www.motiondsp.com/ncis-surveillance-video/

(N.d.). Retrieved 19 September 2024, from http://america.pink/bilinear-interpolation_661297.html

G_, S. (2011, August 7). Zoom an image with different interpolation types. Retrieved 19 September 2024, from CodeProject website: http://www.codeproject.com/Articles/236394/Bi-Cubic-and-Bi-Linear-Interpolation

Bevilacqua, M., Roumy, A., Guillemot, C., & Morel, M. L. A. (n.d.). Low complexity singleimage super-resolution based on nonnegative neighbor embedding. British Machine.

Jin, M., Jin, J., & Hao, G. (2012). Optimization design for eye-in-hand robotics Based on A New Binocular Stereo Vision Servoing Model. Proceedings of the 2nd International Conference on Electronic and Mechanical Engineering and Information Technology (2012). Presented at the 2nd International Conference on Electronic and Mechanical Engineering and Information Technology, China. doi:10.2991/emeit.2012.118 DOI: https://doi.org/10.2991/emeit.2012.118

Low-Complexity Single-Image Super-Resolution. (n.d.). Retrieved 19 September 2024, from http://people.rennes.inria.fr/Aline.Roumy/results/SR_BMVC12.html

Research. (n.d.). Retrieved 19 September 2024, from https://sites.google.com/site/romanzeyde/research-interests