Robust ReadingCompetition
Challenges

Overview - Incidental Scene Text

Challenge 4 will focus on real scene images similarly to Challenge 2. Contrary to Challenge 2 which is based on images focused on the text content (well-captured, horizontal English text, typically centred in the image), Challenge 4 will focus on incidental scene text.

Incidental scene text refers to text that appears in the scene without the user having taken any specific prior action to cause its appearance or improve its positioning / quality in the frame. While focused scene text is the expected input for applications such as translation on demand, incidental scene text covers another wide range of applications linked to wearable cameras or massive urban captures where the capture is difficult or undesirable to control.

This challenge was introduced for the 2015 edition of the competition, and three tasks are available : Text Localisation, Word Recognition and End-to-End. See details in the Tasks page.

The results from the ICDAR 2015 competition can be found in the ICDAR proceedings [1].

[1] D. Karatzas, L. Gomez-Bigorda, A. Nicolaou, S. Ghosh, A. Bagdanov, M. Iwamura, J. Matas, L. Neumann, V.R. Chandrasekhar, S. Lu, and F. Shafait, "ICDAR 2015 competition on robust reading. In Document Analysis and Recognition (ICDAR), 2015 13th International Conference on (pp. 1156-1160). IEEE. [paper] [presentation]

Challenge4_Overview_v02.png

Important Dates