In this project, the Auto Encoder architecture will be applied in deep learning to denoising Images.
In this project, I used data from Kaggel " Alzheimer's MRI images", and applied NOISE to it (imgPX*0.25).
On the left is the original image and on the right is after applying Noise.
🔗Dataset in kaggle : Alzheimer MRI Preprocessed Dataset
🔗 NoteBooks in Kaggel Denoising Alzheimer MRI - Auto Encoder
The result of this model was:
696 images in train and 100 in Validation and 100 in Test ,
- loss: 0.2959 - val_loss: 0.2949 After 500 Epoch.
- Evaluate : 0 .2974
- Avg of peak signal noise ratio : 21.889
The following tools were used in this project:
