Scene Text Localisation in the KAIST Dataset

Datasets -> Current Page

Created: 2010-01-25 Last updated: 2011-001-27

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.

Related Dataset

• KAIST Scene Text Database

Related Ground Truth Data

• KAIST Scene Text Ground Truth (text location, segmantation and recognition)

Related Software

None

References

1. S.M. Lucas and et al, "ICDAR 2003 Robust Reading Competitions: Entries, Results and Future Directions," International Journal on Document Analysis and Recognition, vol. 7, pp. 105-122, 2005.
2. Simon Lucas, "ICDAR 2005 Text Locating Competition Results," in Proceedings of the 8th International Conference on Document Analysis and Recognition, Seoul, S. Korea, 2005, pp. 80-84.
3. Christian Wolf and Jean-Michel Jolion, "Object Count / Area Graphs for the Evaluation of Object Detection and Segmentation Algorithms," International Journal of Document Analysis, vol. 8, no. 4, pp. 280-296, 2006.

---

This page is editable only by TC11 Officers .