Face Sketch Synthesis and Recognition

Xiaogang Wang and Xiaoou Tang

Introduction

An important application of face recognition is to assist law enforcement. Automatic retrieval of photos of suspects from police mug-shot database can help the police narrow down potential suspects quickly. However, in most cases, the photo image of a suspect is not available. The best substitute is often a sketch drawing based on the recollection of an eyewitness. Therefore, automatically searching through a photo database using a sketch drawing becomes important. It can not only help police to locate a group of potential suspects, but also help the witness and the artist to modify the sketch drawing of the suspect interactively based on similar photos retrieved. However due to great difference between sketches and photos and the unknown psychological mechanism of sketch generation, face sketch recognition is much harder than normal face recognition based on photo images. It is difficult to perform the sketch-photo match in two different modalities. One way to solve this problem is to first transform face photo into sketch drawing and then match the query sketch with the synthesized sketch in the same modality. Face sketch synthesis can not only help face sketch recognition, but also has many other useful applications in entertainment industry, thus has drawn board interest. In this paper, we will study these two interesting and related problems, face sketch/photo synthesis and face sketch recognition. We proposed two approaches using global Eigentransformation and multi-scale Markov Random Field to synthesize a sketch given a photo or synthesize a photo given a sketch drawn by the artist.

Face Sketch Synthesis Using the Global Eigentransformation

Photo	Synthesized sketch	Sketch drawn by the artist		Photo	Synthesized sketch	Sketch drawn by the artist

Face Sketch Synthesis Using the Multi-Scale Markov Random Field

Find results here.