Title :
Drop Caps Decomposition for Indexing a New Letter Extraction Method
Author :
Coustaty, Mickael ; Ogier, Jean-Marc ; Pareti, Rudolf ; Vincent, Nicole
Author_Institution :
Imedoc Team, L3i Lab., La Rochelle, France
Abstract :
This paper present a new method to extract shapes in drop caps and particularly the most important shape: letter itself. This method relies on a combination of a Aujol and Chambolle algorithm first, and a segmentation using a Zipf law in a second step. This method can be enhanced as a three-step process: 1) decomposition in layers 2) segmentation using a Zipf law 3) selection of connected components to only emphasize the required information - letter itself.
Keywords :
database indexing; document image processing; feature extraction; image segmentation; object recognition; shape recognition; statistical analysis; Aujol-and-Chambolle algorithm; Zipf law; connected component selection; drop caps decomposition; drop caps recognition; empirical law; image segmentation; letter extraction method; printed document image processing; shape extraction; structure-based indexing; three-step process; Books; Data mining; Degradation; Graphics; Indexing; Information analysis; Laboratories; Printing; Shape; Text analysis; Decomposition; Drop Caps; Meyer; Old Documents; Segmentation; Zipf´ Law;
Conference_Titel :
Document Analysis and Recognition, 2009. ICDAR '09. 10th International Conference on
Conference_Location :
Barcelona
Print_ISBN :
978-1-4244-4500-4
Electronic_ISBN :
1520-5363
DOI :
10.1109/ICDAR.2009.233
