Photo-sketch synthesis and recognition based on subspace learning

This paper aims to reducing difference between sketches and photos by synthesizing sketches from photos, and vice versa, and then performing sketch–sketch/photo–photo recognition with subspace learning based methods. Pseudo-sketch/pseudo-photo patches are synthesized with embedded hidden Markov model. Because these patches are assembled by averaging their overlapping area in most of the local strategy based methods, which leads to blurring effect to the resulted pseudo-sketch/pseudo-photo, we integrate the patches with image quilting. Experiments are carried out to demonstrate that the proposed method is effective to produce pseudo-sketch/pseudo-photo with high quality and achieve promising recognition results.