1. An image super-resolution method based on polynomial exponential function and non-uniform rectangular partition.
- Author
-
Zhao, Weikang, U, KinTak, and Luo, Huibin
- Subjects
- *
HIGH resolution imaging , *IMAGE segmentation , *POLYNOMIALS , *PROBLEM solving , *IMAGE reconstruction algorithms - Abstract
Image texture features and details are extremely important in image super-resolution. Meanwhile, preserving image texture features and details with less running time is also a significant problem to be solved. This paper proposes an image super-resolution method based on polynomial exponential function and non-uniform rectangular partition to restore the image structure and the details of edges and textures. The algorithm performs least-squares fitting according to the image grayscale to divide the low-resolution image into several different rectangular regions. By substituting the coordinates into each regional polynomial exponential function, the approximated regional high-resolution sub-image can be obtained to form the final whole high-resolution image. The proposed method can better represent the image textures in complex regions and effectively preserve edge details and suppress artifacts. The experimental results demonstrate that the proposed method is significantly superior to the state-of-the-art methods in the terms of subjective vision, objective quantitative evaluation, and execution time. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF