Information Extraction from Old Images of Documents for Indexing
Mickaël Coustaty, Sloven Dubois, Jean-Marc Ogier, Michel Ménard · 2009
Abstract. This paper present a new method to extract areas of interest in drop caps and particularly the most important shape: Letter itself. This method relies on a combination of a Aujol and Chambolle algorithm and a Segmentation using a Zipf Law and can be enhanced as a three-step process: 1)Decomposition in layers 2)Segmentation using a Zipf Law 3)Selection of the connected components.