9th International Conference on ICT for Sustainable Development

Authors - Pranali Dandekar, Shailendra S. Aote
Abstract - In recent years, the demand for high-resolution images has surged across various domains, including surveillance, medical imaging, and remote sensing. However, capturing high-resolution images can be constrained by factors such as hardware limitations or bandwidth constraints. To address this challenge, super-resolution techniques aim to reconstruct high-resolution images from their low-resolution counterparts. In this paper, we propose a novel approach that combines deep convolutional neural networks (CNNs) with bicubic interpolation to achieve superior super-resolution performance. Our method leverages the powerful feature extraction capabilities of deep CNNs to learn complex mappings between low-resolution and high-resolution image spaces. Additionally, we incorporate bicubic interpolation as a preprocessing step to enhance the input resolution, providing the CNN with more detailed information to facilitate accurate reconstruction. Experimental results demonstrate that our proposed method outperforms existing state-of-the-art approaches in terms of both PSNR and SSIM measure. Overall, our work contributes to advancing the field of super-resolution by offering an effective and efficient solution for enhancing low-resolution images.