Generation of Facial Drawings Using Generative Adversarial Networks

Abstract

Facial sketches are widely used in judicial and legal proceedings. Law enforcers use facial sketches to help them with the visual aspects of the case, using witness descriptions and video footage. However, drawing forensic sketches by hand is a time-consuming procedure and a situation may arise where the authorities have less time in hand to solve a case. The present research work aims to create a basic model which can generate facial images from a given set of input features; similar to what a forensic artist does, thus, enabling a faster and efficient sketching procedure. In this work, a category of generative algorithms, called Generative Adversarial Networks has been used to build this model. To train this model, a dataset of anime girls has been used and thus it can only generate the same, making sure that the generated image contains the input features.