Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{155815,
        author = {N. Poorna Chandra and B. Anuradha},
        title = {IMAGE DENOISING USING DEEP CONVOLUTIONAL AUTO-ENCODER},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {9},
        number = {2},
        pages = {0-0},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=155815},
        abstract = {Image denoising is one of the fundamental problems in the image processing field since it is required by many computer vision applications like in medical, environmental, educational, and communication. Several methods have been applied in image denoising techniques in recent years from spatial filtering to model-based approaches. The neural network-based objective methods have gained popularity in recent years. However, most of these approaches still have trouble adapting to different noise levels and types. This work presents the denoising of images using the convolutional auto encoder model in deep learning. It has become an important task to remove noise from the image and restore a high-quality image in order to process the image further for a purpose like object segmentation, detection, tracking, etc. This work is done by adding 1% to 10% noise to the image and then applying the auto encoder model to denoise it. In this work there are two types of noise are applied, one is additive white Gaussian noise (AWGN) and another one is salt & pepper noise at different variance levels(σ=3,7,10). The denoised image is next subjected to qualitative and quantitative analysis using two metrics which are MSE (mean square error) and PSNR (peak signal to noise ratio). Here the auto encoder model mainly consists of the encoder and decoder network layers that will help in making the image to be denoised. The results from the analysis and simulation show that the auto encoder model can efficiently remove noise and restore the image details.},
        keywords = {},
        month = {},
        }