This project is an implementation of a Deep Convolutional Denoising Autoencoder to Image denoising using convolutional denoising autoencoders

The names of the notebook indicate the dataset names used to train the models. To see the code running follow these steps

1. Install tensorflow, scipy, keras, pickle and jupyter notebook
2. Open required notebook using jupyter notebook
3. Change directory path of dataset and you are good to go!

1. Denoising Dirty Documents : Denoising Dirty Documents : Remove noise from printed text
2. Super Image Resolution : Super Image Resolution : Image Super Resolution (x4) Using a Generative Adversarial Network

1. Person-Segmentation-Keras
2. Image Denoising with Generative Adversarial Network
3. Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
4. Extending Keras' ImageDataGenerator to Support Random Cropping
5. Mnist denoising autoencoder