2006 | OriginalPaper | Chapter
Style Strokes Extraction Based on Color and Shape Information
Authors : Jianming Liu, Dongming Lu, Xiqun Lu, Xifan Shi
Published in: Advances in Multimedia Information Processing - PCM 2006
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Taking Dunhuang MoGao Frescoes as research background, a new algorithm to extract style strokes from fresco images is proposed. All the pixels in a fresco image are classified into either the stroke objects or the non-stroke objects, and the strokes extraction problem is defined as the process of selecting pixels that forms stroke objects from a given image. The algorithm first detects most likely ROIs (Region-Of-Interest) from the image using stroke color and shape information, and produces a stroke color similarity map and a stroke shape constraint map. Then these two maps are fused to extract style strokes. Experimental results have demonstrated its validity in extracting style strokes under certain variations. This research has the potential to provide a computer aided tool for artists and restorers to imitate and restore time-honored paintings.