Structural optimization of self-attention hierarchical deep neural network and dynamic one-variable encoding for magnification of digital images

Document Type : Research Paper

Authors

1 PhD. Student of Electrical Engineering, Lorestan university

2 Department of Electrical and Electronics Engineering, Faculty of Engineering Lorestan University

3 Dept. of Computer Engineering, lorestan university

Abstract

Enlarging digital images is one of the image processing methods, which improves the image in the field of computer vision. Basically, this is used to zoom in on still and moving images that have passed the time of their capture and there is no access to the camera or scenes to zoom. In this article, a hierarchy is proposed to extract high-level features to solve the demarcation challenge between colors and self-learning attention blocks to reduce convolution operations. In the following, to optimize the network, random search and binary division are used to find optimal answers and meta-parameters. Using the mentioned search method, in addition to searching for network weights and networks, I can also search for the architecture of the structure, this action will automatically generate meta-parameters and optimize the network structure. To check the effectiveness of the proposed method, simulation results on the database in this area have been determined, which show that the proposed method is superior to other methods. According to the results obtained in architecture, by using the four-fold magnification mentioned in the four-story series block and using the attention block in the magnification section, the display-to-noise number was 32.66.

Keywords

Journal of Machine Vision and Image Processing
Volume 10, Issue 3
September 2023
Pages 47-63

Files

Share

How to cite

Statistics