Abstract:

The main goal of this project is to built a web page for getting an enhanced images. This webpage takes an input of low light images and produces an enhanced images of the input low light images. Low-light images often suffer from poor quality, low contrast, and high noise levels, which can hinder their usefulness in various applications. In recent years, convolutional neural network (CNN) models have emerged as a powerful tool for enhancing low-light images. In this study, we propose a CNN-based approach for enhancing low-light images by using a combination of an encoder-decoder architecture and a skip connection to preserve image details. The proposed CNN model is trained on a large dataset of low-light images to learn the mapping between input images and their corresponding enhanced versions. The model is designed to adjust the brightness and contrast of the images while preserving the natural color distribution and suppressing the noise in the dark regions. To evaluate the performance of the proposed approach, we conduct experiments on various low-light images and compare the results with other state-of-the-art methods

Description:

Low light Image Enhancement, CNN Model, Deep learning