Towards Criminal Sketching with Generative Adversarial Network

Criminal sketching aims to draw an approximation portrait of the criminal suspect based on details of the criminal suspect that the observer can remember. However, even for a professional artist, it needs much time to complete sketching and draw a good portrait. In this work, we focus on forensic sketching using a generative adversarial network (GAN) based architecture, which allows us to synthesize a real-like portrait of a criminal suspect described by an eyewitness. The proposed framework consists of two steps: sketch generation and portrait generation. For the former, a facial outline is sketched based on the descriptive details. For the latter, the facial details are completed to generate a portrait. To make the portrait more realistic, we use a portrait discriminator, which can not only learn the discriminative features between the faces synthesized by the generator and the real faces, but also recognize the face attributes. Experiments have shown that the proposed work achieves promising performance for criminal sketching.