Abstract:
Our semi-supervised learning algorithm for single image dehazing works well. The algorithm uses a deep CNN with supervised and unsupervised learning branches. In the supervised branch, mean squared, perceptual, and adversarial losses constrain the deep neural network.
Clean images’ sparsity of dark channel and gradient priors constrain the network in the unsupervised branch. We train the proposed network on synthetic data and real-world images end-to-end.
We found that the semi-supervised learning algorithm can be applied to real-world images. Experimental results show that the proposed algorithm outperforms state-of-the-art single image dehazing algorithms on benchmark datasets and real-world images.
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
