Rain detection via deep convolutional neural networks- Deep Learning projects-Matlab
In this project,deep convolutional neural network is used for rain detection.Recently, sparse coding and dictionary learning have been widely used for feature learning and image processing. They can also be applied to the rain removal by learning two types of rain and non-rain dictionaries.
In the proposed method,masked rain images are used to learn the rain dictionary.Therefore,rain features can be extracted via DCNN from the masked rain images.similarly,non-rain features can also be extracted.DCNN can be trained with the two types of rain and non-rain feature sets.In rain regions,correlation matrix between rain and non-rain dictionaries is calculated.
The experimental results show that the proposed approach using the shrinkage of the sparse codes can preserve image structures and avoid the edge artifacts in the non-rain regions, while removing the rain structures in the rain regions.