Random sampling for fast face sketch synthesis

Face sketch synthesis plays an important role in both digital entertainment and law enforcement. It generally consists of two parts: neighbor selection and reconstruction weight representation. State-of-the-art face sketch synthesis methods perform neighbor selection online in a data-driven manner by K nearest neighbor (K-NN) searching. However, the online search increases the time consuming for synthesis. Moreover, since these methods need to traverse the whole training dataset for neighbor selection, the computational complexity increases with the scale of the training database and hence these methods have limited scalability. In addition, state-of-the-art methods consider that all selected neighbors contribute equally to the reconstruction weight computation process while the distinct similarity between the test patch and these neighbors are neglected. In this paper, we employ offline random sampling in place of online K-NN search to improve the synthesis efficiency. Locality constraint is introduced 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 will release the source codes of our proposed methods and the evaluation metrics for future study online: http://www.ihitworld.com/RSLCR.html.