A detail enhancement strategy for face sketch synthesis based on NSST
Weiguo Wan, Hyo Jong Lee · 2017
Face sketch synthesis plays an important role in both law enforcement and digital entertainment. The existing methods for sketch synthesis always suffer from noising and blurring effect. To resolve these problems, a nonsubsampled Shearlet transform (NSST) based detail enhancement strategy is proposed. The exemplar-based method is firstly adopted to synthesize the primary sketch, then the final sketch can be achieved by extracting and merging the detail information of the test photo to the primary sketch through NSST decomposition and reconstitution. Extensive experiments on public datasets shows that the proposed strategy can obtain outperform target sketches both from subjective and objective comparison.