Random sampling for fast face sketch synthesis

Exemplar-based face sketch synthesis plays an important role in both digital entertainment and law enforcement. It generally consists of two parts: neighbor selection and recognition weight representation. In this paper, we proposed a simple but effective method which employs offline random sampling instead of K-NN used in state-of-the-art methods. The proposed random sampling strategy reduces the time consuming for synthesis and has stronger scalability than state-of-the-art methods. In addition, we introduced locality constraint to model the distinct correlations between the test patch and random sampled patches. Extensive experiments on public face sketch databases demonstrate the superiority of the proposed method in comparison to state-of-the-art methods, in terms of both synthesis quality and time consumption. The proposed method could be extended to other heterogeneous face image transformation problems such as face hallucination. We release the source codes of our proposed methods and the evaluation metrics for future study online: http://www.ihitworld.com/RSLCR.html.