Segmenting and Indexing Old Documents Using a Letter Extraction

Mickaël Coustaty (1) , Sloven Dubois (1) , Jean-Marc Ogier (1) , Michel Menard (1)

1 L3I - Laboratoire Informatique, Image et Interaction - EA 2118

This paper presents 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.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement du texte et du document

Mickaël Coustaty, Sloven Dubois, Jean-Marc Ogier, Michel Menard. Segmenting and Indexing Old Documents Using a Letter Extraction. Jean-Marc Ogier, Wenyin Liu, Josep Llados. Graphics Recognition. Achievements, Challenges, and Evolution, Springer Berlin / Heidelberg, pp.142-149, 2010, Lecture Notes in Computer Science - Volume 6020, ⟨10.1007/978-3-642-13728-0_13⟩. ⟨hal-00498379⟩