Overview - Focused Scene Text

Challenge 2 is focused on the reading of text in real scenes. The particular scenario examined is that of "focused text", referring to images of text explicirty focused around the text content of interest. This is the typical scenario for text reading and text translating applications, where the user is explicitly directing the focus of the camera on the text content of interest. At the same time, this is the typical scenario addressed by most methods and datasets up to date. As such, Challenge 2 images usually feature text which is reasonably well focused, and in most of the cases horizontal. The scenario of incidental text is tackled from the 2015 edition of the competition through the new Challenge 4.

The ICDAR 2015 edition of Challenge 2 will follow the successful running of the previous editions of the competition in 2011 and 2013. The 2013 edition, which is the definitive one for the tasks of text localisation, text segmentation and word recognition, was opened to the community in a continuous mode after ICDAR 2013. These tasks are still open for participation but will not be the main focus of the 2015 edition.

The 2015 edition of the Challenge features a new task on End-to-End systems, referring to text localisation and recognition in a single go at the word level. The rest of the tasks remain open in a continuous mode, unchanged form the 2013 edition. See details in the Tasks page.

The results from the past ICDAR competitions can be found in the ICDAR proceedings [1, 2]. The original paper introducing the dataset is [3].

1. D. Karatzas, F. Shafait, S. Uchida, M. Iwamura, L. Gomez, S. Robles, J. Mas, D. Fernandez, J. Almazan, L.P. de las Heras , "ICDAR 2013 Robust Reading Competition", In Proc. 12th International Conference of Document Analysis and Recognition, 2013, IEEE CPS, pp. 1115-1124. [pdf] [poster] [presentation]

2. A. Shahab, F. Shafait, A. Dengel, "ICDAR 2011 Robust Reading Competition - Challenge 2: Reading Text in Scene Images",  In Proc. 11th International Conference of Document Analysis and Recognition, 2011, IEEE CPS, pp. 1491-1496. [pdf]

3. S.M. Lucas et al, "ICDAR 2003 Robust Reading Competitions: Entries, Results and Future Directions", Int. Journal on Document Analysis and Recognition, Vol. 7, Num. 2-3, pp. 105-122, 2005