What is it about?
Image denoising methods are of fundamental importance in the image processing area. In this work, we analyze the traditional and state of the art mathematical models for computational color image denoising based on the partial differential equations, low rank, sparse representation and recent developments based on deep learning models.
Photo by Markus Spiske on Unsplash
Why is it important?
The natural images are corrupted with the noise due to the thermal effects in image acquisition system, varying spatial resolution, moving objects in scene, online data transferee, compression and many other reasons. Clean and enhanced edges are the requirement of many post processing applications such as object detection, labeling, image segmentation and image interpretation. This gives rise to the image denoising models that are building blocks in devising robust artificial intelligence methods for visual data. In this work, we considered computational denoising methods that are based on partial differential equations (PDEs) and deep learning models.
Read the Original
This page is a summary of: Recent developments in computational color image denoising with PDEs to deep learning: a review, Artificial Intelligence Review, March 2021, Springer Science + Business Media, DOI: 10.1007/s10462-021-09977-z.
You can read the full text:
The following have contributed to this page