With the advent of social networking services such as Facebook and Instagram, there has been a huge increase in the volume of image data generated in the last decade. The use of image (and video) processing software like Adobe Photoshop to create doctored images and videos is a major concern for internet companies like Facebook. These images are prime sources of fake news and are often used in malevolent ways such as for mob incitement. Before action can be taken on basis of a questionable image, we must verify its authenticity.
Inspired to contribute towards solving this social issue, I made my own custom architecture-based model for Fake Image Detection and Segmentation. For Future Scope, I am aiming to host my model to a browser-based web application for helping researchers experiment using their own data and for the general public's use.