Fast patch-wise image retargeting

Yichi Zhang, King Ngi Ngan

Abstract: Content-aware image retargeting adjusts images to arbitrary sizes and preserves visually salient content. Previous algorithms formulate the problem in terms of either pixel level or mesh level structures, deforming salient objects inconsistently. To improve retargeting quality and reduce complexity, we introduced a patch-wise method to generate sparse image grids based on visual saliency and gradient magnitude. Three energy functions were optimized to warp the grids and generate retargeted images. Experimental results on the public database RetargetMe show that this patch-wise retargeting algorithm has lower complexity and performs slightly better than other algorithms using much denser grids.