Image Denoising: An Overview of Noise Model, Denoising Methods and Applications

• Abdulkabiru A. ABDULRAZAQ

  Author

• Abideen A. ISMAIL

  Author

• Muhammad S. NAZRUL-ISLAM

  Author

• Akeem R. ABIOYE

  Author

• Margaret D. OKPOR

  Author

• Paschal, U. CHINEDU

  Author

In recent years, image denoising has found its way into numerous applications, ranging from medical diagnosis to psychological education, where noise reduction plays a crucial role in improving the clarity and usability of visual data. In the field of computer vision, image denoising is considered a vital preprocessing step for a variety of image analysis tasks, including object detection, image segmentation, and feature extraction. This paper explores the fundamentals of noise models and their impact on image quality, demonstrating how different types of noise can degrade essential image details. A variety of denoising methods are presented, categorized into spatial filtering, transform domain, and machine learning-based approaches. Through a review of recent publications, this paper highlights the growing dominance of machine learning-based methods, which have been shown to outperform conventional techniques due to their ability to learn complex noise patterns and generalize across diverse datasets. However, the study also identifies potential challenges associated with machine learning methods, particularly concerning the availability of large, high-quality training datasets and the computational resources required to train these models effectively. These limitations create new direction for future research, aimed at optimizing machine learning techniques for more efficient and accessible image denoising solutions.

• FJET_21_51_51

Copyright (c) 2026 FUDMA Journal of Engineering and Technology

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.