Title :
Color text extraction from camera-based images: the impact of the choice of the clustering distance
Author :
Mancas-Thillou, Céline ; Gosselin, Bernard
Author_Institution :
Faculte Polytechnique de Mons, Belgium
fDate :
29 Aug.-1 Sept. 2005
Abstract :
Character recognition has a continuous importance for several years and recently, new challenges appeared with camera-based pictures. This paper deals with text extraction for color natural scenes images. Many papers try to combine several color spaces or to choose the best one for a particular database. We show that the main problem is not in the choice of color spaces for generic text extraction but in the choice of clustering distances to handle alt degradations present in this kind of images. Comparative results are given using a public database.
Keywords :
document image processing; feature extraction; image colour analysis; image segmentation; natural scenes; optical character recognition; pattern clustering; text analysis; visual databases; camera-based images; camera-based pictures; character recognition; clustering distance; color natural scenes images; color text extraction; Character recognition; Data mining; Degradation; Image color analysis; Image databases; Image segmentation; Layout; Optical character recognition software; Robustness; Text analysis;
Conference_Titel :
Document Analysis and Recognition, 2005. Proceedings. Eighth International Conference on
Print_ISBN :
0-7695-2420-6
DOI :
10.1109/ICDAR.2005.76
