This goal if this project is to enhance the resolution of any given image with the help of Deep Learning. With a a data set of high resolution and corresponding low resolution images, this can be achieved.

Given a grayscale image, using convolutional neural network, it is possible to apply colour to the image. Given enough data, the CNN model can learn to predict the coloured version of the image bsaed on the content in the image.

In this project, the model is trained to colour grayscale images of the following category:

People's faces
Coast
Buildings
Mountains
Forests
Open country
Street
City Center

A visualisation tool for the following sorting algorithms made with Unity 3D game engine.

Bubble sort
Insertion sort
Selection sort
Gnome sort
Cocktail sort

Any image classification problem requires the model to learn features of objects in the dataset. If the objects have high level features such as complex shapes, colors, etc. then the model would require lot of data to learn these features. A pretrained model is a model that was previously trained on a large dataset, typically on a large-scale image-classification task. If this original dataset is general enough, then the spatial hierarchy of features learned by the model can effectively act as a generic model of the visual world, and hence its features can prove useful for our problem, even though the classes in our problem are completely different. This technique is called Transfer Learning.