• Nelli Priyanka
• Maruvada Sailaja

An image may be disturbed by impulse noise during transmission or acquisition. For image processing applications, it is crucial to repair the disturbed image effectively. This research proposes an encoder-decoder architecture with separate convolution layers to address the problems with low-light picture improvement. Using both clean and noisy photos from an unique low-light image dataset (LID), the architecture is trained from beginning to end. Convolutional Resnet architecture is used in this research to aid in the extraction of the image's features. The top signal-to-noise ratio, the primary comparability record network, the visual data devotion, and the average brightness are some of the evaluation measurements. Using the Matlab tool, the experimental results were produced.

"Enhancement Of Lower Visible Images Using Convolutional Resnet", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 10, page no.e522-e529, October-2022, Available :http://www.jetir.org/papers/JETIR2210472.pdf

"Enhancement Of Lower Visible Images Using Convolutional Resnet", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 10, page no. ppe522-e529, October-2022, Available at : http://www.jetir.org/papers/JETIR2210472.pdf