Image super resolution through two-dimensional wavelet transform
Abstract
Super resolution (SR) is a technique aimed at enhancing the spatial resolution of low-resolution digital images (LR). In contrast to interpolation-based algorithms that often introduce distortions or irregular borders, the algorithm proposed in this article preserves the edges of the original image by interpolating the detail sub-bands derived from the Discrete Wavelet Transform (DWT). The wavelet decomposition was conducted using three different families: Daubechies, Symlet, and Coiflet. Subsequently, all the interpolated sub-band images are combined to generate the SR image. The results obtained demonstrate excellent performance in terms of objective metrics, including execution time, SSIM, and PSNR (1.669 sec., 0.8908, and 30.61 dB, respectively, for 4080x2712 super resolution images). Moreover, subjective metrics based on human visual perception also indicate favorable outcomes across various images.
Downloads
References
Tamrakar, A. & Ortega, A. (2005). Base de datos de imágenes USC-SIPI. https://sipi.usc.edu/database/
Bhatt, U., Singh, A., Bhadauria, H. S., & Kumar, M. (2016). Image super resolution based on discrete and stationary wavelet transform using canny edge extraction and non local mean. In 2016 International Conference on Inventive Computation Technologies (ICICT) (Vol. 3, pp. 1-5). IEEE. https://doi.org/10.1109/inventive.2016.7830216.
Chavez-Roman, H., Ponomaryov, V., & Peralta-Fabi, R. (2012). Image super resolution using interpolation and edge extraction in wavelet transform space. In 2012 9th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE) (pp. 1-6). IEEE. https://doi.org/10.1109/ICEEE.2012.6421202.
Agustsson, E., & Timofte, R. (2017). Ntire 2017 challenge on single image super-resolution: Dataset and study. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops (pp. 126-135).
Pappas, T. N., Safranek, R. J., & Chen, J. (2000). Perceptual criteria for image quality evaluation. Handbook of image and video processing, 110.
Sowmya, K. (2016). Single image super resolution with wavelet domain transformation and sparse representation. International Journal of Innovative Research in Computer Science & Technology (IJIRCST), 4.
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4). https://doi.org/600-612. 10.1109/TIP.2003.819861
Copyright (c) 2023 Raúl Jair Osorno-Ortiz , Volodymyr Ponomaryov, Rogelio Reyes-Reyes, Clara Cruz-Ramos
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
