Scene Text Localisation in the KAIST Dataset

From TC11
Revision as of 16:35, 27 January 2011 by Dimos (talk | contribs) (Created page with '=Description= The aim of this task is to automatically find bounding boxes of text at word level and character level in the KAIST dataset images. The bounding boxes should be ho…')
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Description

The aim of this task is to automatically find bounding boxes of text at word level and character level in the KAIST dataset images.

The bounding boxes should be horizontal.

The evaluation method to be used should be the same as defined for the ICDAR 2003 (and 2005) "Robust Reading Competitions" [1, 2]. The performace is evaluated as precision and recall score of the bounding boxes.

Retrieved from "http://iapr-tc11.org/mediawiki/index.php?title=Scene_Text_Localisation_in_the_KAIST_Dataset&oldid=1301"