Team, Visitors, External Collaborators
Overall Objectives
Research Program
Highlights of the Year
New Software and Platforms
New Results
Bilateral Contracts and Grants with Industry
Partnerships and Cooperations
XML PDF e-pub
PDF e-Pub

Section: New Results

Improving Face Sketch Recognition via Adversarial Sketch-Photo Transformation

Participants : Antitza Dantcheva, Shikang Yu [Chinese Academy of Sciences] , Hu Han [Chinese Academy of Sciences] , Shiguang Shan [Chinese Academy of Sciences] , Xilin Chen [Chinese Academy of Sciences] .


Face sketch-photo transformation has broad applications in forensics, law enforcement, and digital entertainment, particular for face recognition systems that are designed for photo-to-photo matching. While there are a number of methods for face photo-to-sketch transformation, studies on sketch-to-photo transformation remain limited. In this work, we proposed a novel conditional CycleGAN for face sketch-to-photo transformation. Specifically, we leveraged the advantages of CycleGAN and conditional GANs and designed a feature-level loss to assure the high quality of the generated face photos from sketches. The generated face photos were used, as a replacement of face sketches, and particularly for face identification against a gallery set of mugshot photos. Experimental results on the public-domain database CUFSF showed that the proposed approach was able to generate realistic photos from sketches, and the generated photos were instrumental in improving the sketch identification accuracy against a large gallery set. This work has been presented at the IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019) [30].

Figure 10. Overview of the proposed GAN for sketch-to-photo transformation using feature-level loss.