Local face sketch synthesis learning

Publication Type:
Journal Article
Neurocomputing, 2008, 71 (10-12), pp. 1921 - 1930
Issue Date:
Filename Description Size
Thumbnail2011000285OK.pdf1.6 MB
Adobe PDF
Full metadata record
Facial sketch synthesis (FSS) is crucial in sketch-based face recognition. This paper proposes an automatic FSS algorithm with local strategy based on embedded hidden Markov model (E-HMM) and selective ensemble (SE). By using E-HMM to model the nonlinear relationship between a photo-sketch patch pair, a series of pseudo-sketch patches, generated based on several learned models for a given photo patch, are integrated with SE strategy to synthesize a finer face pseudo-sketch patch. Finally, the intact pseudo-sketch can be generated by combining all synthesized patches. Experimental results illustrate that the proposed FSS algorithm works well. © 2008 Elsevier B.V. All rights reserved.
Please use this identifier to cite or link to this item: