Abstract:
Haze, smoke, fog, rain, and snow degrade outdoor images/videos. Due to weather, haze is most common in outdoor scenes. This paper proposes MSRL-DehazeNet, a deep learning-based architecture for single image haze removal using MSRL and image decomposition.
Instead of learning an end-to-end mapping between each pair of hazy images and their corresponding haze-free ones, most learning-based approaches restore the image base component.
Our multi-scale deep residual learning and simplified U-Net learning can dehaze a hazy image by mapping between hazy and haze-free base components, while the other learned convolutional neural network (CNN) enhances the detail component.
Our deep residual CNN architecture and simplified U-Net structure allow feature maps (produced by extracting structural and statistical features) and each previous layer to be fully preserved and fed into the next layer.
Thus, recovering the image without color distortion. Thus, integrating the haze-removed base and enhanced detail image components yields the final dehazed image. The proposed framework outperformed state-of-the-art approaches in experiments.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
