|
|
|
| e-Pub |
Previous | 
Home
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] .
participants
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].
