Year: 2024
Type: article
Abstract: The primary objective of the project is to enhance techniques for super-resolution picture enhancement. Superresolution aims to reconstruct high-resolution images from lower-resolution inputs in order to address the drawbacks of conventional imaging systems. Utilizing the most recent deep learning architectures, the research employs convolutional neural networks (CNNs) and innovative techniques to achieve high picture resolution. The model is trained on large datasets of highand low-resolution picture pairings, enabling it to recognize intricate patterns and nuances that enable it to generate significantly better images. By examining various deep learning architectures and optimization strategies, the research aims to push the boundaries of super-resolution capabilities. Image processing is advanced by the research's practical applications in fields like satellite imagery, surveillance systems, and medical imaging.
Author: Sudipa Kower
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4405209024