Deep Learning based Automated Image Deblurring

• Published in: E3S web of conferences 2023-01, Vol.430, p.1052
• Main Authors: Shruthi, Ch.M., Ramachandra Anirudh, Vemullapalli, Bhargava Rao, Palla, Shiva Shankar, Birru, Pandey, Akhilesh
• Format: Article
• Language: English
• ISSN: 2267-1242; 2267-1242
• DOI: 10.1051/e3sconf/202343001052

Image deblurring is a challenging task that aims to restore a sharp and clear image from a blurred one. This problem is usually caused by camera motion or defocus blur. The objective of this paper is to develop a model that can effectively remove Gaussian blur from an image and improve its quality using deep learning techniques. Automated image deblurring is achieved using deep learning, this approach involves implementing a combination of convolutional neural networks (CNN) and simple auto encoders to train the model on a dataset of blurred and corresponding sharp images. The model is then used to deblur the test images and improve their quality. The paper uses a dataset of blurred and corresponding sharp images to train the model, and the performance of the model is evaluated based on metrics such as PSNR and SSIM. The results and discussions focus on the effectiveness of the model in removing Gaussian blur and improving the quality of the images. In conclusion, the paper demonstrates the effectiveness of using deep learning techniques for image deblurring and provides scope for future enhancements such as incorporating more complex models and exploring other types of blur removal techniques.