Skip to content

jyothishkjames/Image-Denoising-with-Autoencoders

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

39 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Image-Denoising-with-Autoencoders

Getting Started

Image Deonising with Autoencoders project introduces a novel approach to denoise noisy images with Autoencoders. Here we make use of the Convolutional Autoencoders to build and train a Deep Neural Network which learns to remove noise from an image.

Prerequisites

The following libraries are used for the project:

opencv-python
numpy
scikit-learn
matplotlib
tensorflow

Deep Neural Network Architecture

Alt text

Dataset

In contrast to a classification problem, an autoencoder generates images. Hence we require only a very small dataset as this falls under a regression problem. We train on 200 samples and validate on 100 samples.

How to test the saved model?

Go to the folder model and run the file inference.py

Summary

We have a novel approach with a simple architecture which learns to model gaussian noise.

About

A novel approach for Image denoising with Autoencoders

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published