Random Sampling and Locality Constraint for
Face Sketch Synthesis


Nannan Wang      Xinbo Gao      Jie Li


HIT Group   State Key Laboratory of Integrated Services Networks
Xidian University


RSLCR


Abstract


     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 reconstruction weight representation. The most time-consuming or main computation complexity for exemplar-based face sketch synthesis methods lies in the neighbor selection process. State-of-the-art face sketch synthesis methods perform neighbor selection online in a data-driven manner by K nearest neighbor (K-NN) searching. Actually, 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 this paper, we proposed a simple but effective offline random sampling in place of online K-NN search to improve the synthesis efficiency. 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.



Contribution Highlights


  • Firstly, an offline random sampling strategy is employed to reduce the time consuming for online neighbor selection.
  • Secondly, the proposed random sampling strategy has stronger scalability than state-of-the-art methods due to the fact that the time-consuming does not depend on the scale of training dataset for our proposed strategy while not the case for other methods.
  • Finally, both our proposed RSLCR method and its fast version Fast-RSLCR achieve superior performance than state-of-the-art methods in terms of both synthesis performance and synthesis efficiency. Specially, our proposed Fast-RSLCR could synthesize a sketch using no more than 1.5 seconds on the Chinese University of Hong Kong (CUHK) face sketch FERET database (CUFSF) under the MATLAB environment, which is the fastest exemplar-based face sketch synthesis method.



Codes&Results


  • Our RSLCR & Fast-RSLCR Codes Written in MATLAB [Download];
  • All Syntheisized Sketches both for Our Methods and Six State-Of-The-Art Methods [Download];
  • SSIM Evaluation Codes and Results in Our Paper [Download];
  • NLDA Face Recognition Codes and Results in Our Paper [Download];
  • Our MATLAB Implementation of the LLE Method [Download];
  • Our Implementation of the FCN Method (Based on Caffe) [Download];
  • MRF Source Codes from Dr. Yibing Song [Download];
  • SSD Source Codes From Dr. Yibing Song [Download].



To Top