• Soundharya K
• Srimadhumitha K
• Sangeetha V
• Balachandran G

This paper establishes a deep learning and image-based model for air quality gauging the fog, haze and smoke. Nowadays, these are the major reason for road accidents, plane crash, etc. The fog has less contrast level of image and also affects the visual quality. The air light and attenuation phenomena affect the visual quality of image. Air speck, which present in atmosphere that affects the visibility level of image also it is called as noise or unwanted signal. So, we are improving the visible level of image and bring down the various fog image filtering method that are used. For improving the visual quality level, we are using 4 crucial steps. First step is image pre-processing in this we are using median filter, haze removal, image enhancement, RGB extraction, grey scale image and so on. Secondly, we are using histogram process for that we use adaptive histogram equalization. Then next step is image segmentation used to divide a digital image into multiple image section. Finally, we are using classification to label the set of pixels. Our main motive is to review the improved quality of image which give a clear image in poor atmosphere.

Preprocessing, Segmentation, Classification, Convolutional Neural Network, MATLAB, Arduino IDE, Node MCU

"NOISE – INSENSITIVE AND EDGE PRESERVING RESOLUTION USING SGAR MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 6, page no.f371-f374, June-2022, Available :http://www.jetir.org/papers/JETIR2206542.pdf

"NOISE – INSENSITIVE AND EDGE PRESERVING RESOLUTION USING SGAR MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 6, page no. ppf371-f374, June-2022, Available at : http://www.jetir.org/papers/JETIR2206542.pdf