Introduction

"Robust Reading" refers to the research area dealing with the interpretation of written communication in unconstrained settings. Typically Robust Reading is linked to the detection and recognition of textual information in scene images, but in the wider sense it refers to techniques and methodologies that have been developed specifically for text containers other than scanned paper documents, and include born-digital images and videos to mention a few.

Robust Reading is at the meeting point between camera based document analysis and scene interpretation, and serves as common ground between the document analysis community and the wider computer vision community.

Challenges on this portal have been held since 2011, and are typically associated to the Int. Conference on Document Analysis and Recognition. The portal is organized around challenges that cover a wide range of real-world situations, and have been tracking the evolution of the state of the art. Each challenge is set up around different tasks.

ICDAR 2021 competition on Document Visual Question Answering (DocVQA) 2021

The "Document Visual Question Answering" (DocVQA) challenge, focuses on a specific type of Visual Question Answering task, where visually understanding the information on a document image is necessary in order to provide an answer. This goes over and above passing a document image through OCR, and involves understanding all types of information conveyed by a document. Textual content (handwritten or typewritten), non-textual elements (marks, tick boxes, separators, diagrams), layout (page structure, forms, tables), and style (font, colours, highlighting), to mention just a few, are pieces of information that can be potentially necessary for responding to the question at hand.

The DocVQA challenge is a continuous effort linked to various events. The challenge was originally organised in the context of the CVPR 2020 Workshop on Text and Documents in the Deep Learning Era. The second edition will take place in the context of the Int. Conference on Document Analysis and Recognition (ICDAR) 2021.

Task 2 on "Document Collection VQA" and the new Task 3 on "Infographics VQA" are the focus of the ICDAR 2021 competition. See more details here.

Publications

1. Mathew, M., Bagal, V., Tito, R. P., Karatzas, D., Valveny, E., & Jawahar, C. V. (2022). InfographicVQA. WACV 2022. [arxiv]

2. Tito, R., Karatzas, D., & Valveny, E. (2021). Document Collection Visual Question Answering. ICDAR 2021. [arxiv]

3. Mathew, M., Karatzas, D., Manmatha, R., & Jawahar, C. V. (2020). DocVQA: A Dataset for VQA on Document Images. WACV 2021. [arxiv]

4. Mathew, M., Tito, R., Karatzas, D., Manmatha, R., & Jawahar, C. V. (2020). Document Visual Question Answering Challenge 2020. DAS 2020. [arxiv]

5. Biten, A. F., Tito, R., Mafla, A., Gomez, L., Rusinol, M., Valveny, E., ... & Karatzas, D. (2019). Scene text visual question answering. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 4291-4301). [paper]

6. Biten, A.F., Tito, R., Mafla, A., Gomez, L., Rusinol, M., Mathew, M., Jawahar, C.V., Valveny, E. and Karatzas, D., (2019, September). Icdar 2019 competition on scene text visual question answering. In 2019 International Conference on Document Analysis and Recognition (ICDAR) (pp. 1563-1570). IEEE. [paper][arxiv]

7. Nayef, N., Patel, Y., Busta, M., Chowdhury, P.N., Karatzas, D., Khlif, W., Matas, J., Pal, U., Burie, J.C., Liu, C.L. and Ogier, J.M., (2019, September). ICDAR2019 robust reading challenge on multi-lingual scene text detection and recognition—RRC-MLT-2019. In 2019 International Conference on Document Analysis and Recognition (ICDAR) (pp. 1582-1587). IEEE. [paper][arxiv]

8. Sun, Y., Ni, Z., Chng, C.K., Liu, Y., Luo, C., Ng, C.C., Han, J., Ding, E., Liu, J., Karatzas, D. and Chan, C.S., (2019, September). ICDAR 2019 Competition on Large-Scale Street View Text with Partial Labeling-RRC-LSVT. In 2019 International Conference on Document Analysis and Recognition (ICDAR) (pp. 1557-1562). IEEE. [paper][arxiv]

9. Chng, C.K., Liu, Y., Sun, Y., Ng, C.C., Luo, C., Ni, Z., Fang, C., Zhang, S., Han, J., Ding, E. and Liu, J., (2019, September). ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text-RRC-ArT. In 2019 International Conference on Document Analysis and Recognition (ICDAR) (pp. 1571-1576). IEEE.[paper][arxiv]

10. Huang, Z., Chen, K., He, J., Bai, X., Karatzas, D., Lu, S., & Jawahar, C. V. (2019, September). Icdar2019 competition on scanned receipt ocr and information extraction. In 2019 International Conference on Document Analysis and Recognition (ICDAR) (pp. 1516-1520). IEEE. [paper]

11. Zhang, R., Zhou, Y., Jiang, Q., Song, Q., Li, N., Zhou, K., Wang, L., Wang, D., Liao, M., Yang, M. and Bai, X., (2019, September). ICDAR 2019 robust reading challenge on reading chinese text on signboard. In 2019 International Conference on Document Analysis and Recognition (ICDAR) (pp. 1577-1581). IEEE. [paper][arxiv]

12. M. Iwamura, N. Morimoto, K. Tainaka, D. Bazazian, L. Gomez, D. Karatzas, (2017, November). ICDAR2017 robust reading challenge on omnidirectional video. In Document Analysis and Recognition (ICDAR), 2017 14th IAPR International Conference on (Vol. 1, pp. 1448-1453). IEEE. [paper]

13. R. Gomez, B. Shi, L. Gomez, L. Neumann, A. Veit, J. Matas, S. Belongie, D. Karatzas, (2017, November). ICDAR2017 robust reading challenge on COCO-Text. In 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) (pp. 1435-1443). IEEE. [paper]

14. N. Nayef, F. Yin, I. Bizid, H. Choi, Y. Feng, D. Karatzas, Z. Luo, U. Pal, C. Rigaud, J. Chazalon, W. Khlif, (2017, November). ICDAR2017 Robust Reading Challenge on Multi-Lingual Scene Text Detection and Script Identification-RRC-MLT. In Document Analysis and Recognition (ICDAR), 2017 14th IAPR International Conference on (Vol. 1, pp. 1454-1459). IEEE. [paper]

15. C. Yang, X.C. Yin, H. Yu, D. Karatzas, Y. Cao, (2017, November). ICDAR2017 robust reading challenge on text extraction from biomedical literature figures (DeTEXT). In Document Analysis and Recognition (ICDAR), 2017 14th IAPR International Conference on (Vol. 1, pp. 1444-1447). IEEE. [paper]

16. D. Karatzas, L. Gomez-Bigorda, A. Nicolaou, S. Ghosh, A. Bagdanov, M. Iwamura, J. Matas, L. Neumann, V. Ramaseshan Chandrasekhar, S. Lu, F. Shafait, S. Uchida, E. Valveny, "ICDAR 2015 Competition on Robust Reading", In Proc. 13th International Conference on Document Analysis and Recognition (ICDAR 2015), IEEE, 2015, pp. 1156-1160. [pdf] [presentation]

17. 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]

18. D. Karatzas, S. Robles Mestre, J. Mas, F. Nourbakhsh, P. Pratim Roy , "ICDAR 2011 Robust Reading Competition - Challenge 1: Reading Text in Born-Digital Images (Web and Email)", In Proc. 11th International Conference of Document Analysis and Recognition, 2011, IEEE CPS, pp. 1485-1490. [pdf] [presentation]

19. 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]

20. S.M. Lucas, A. Panaretos, L. Sosa, A. Tang, S. Wong, and R. Young, "ICDAR 2003 robust reading competitions", In Proc. 7th International Conference on Document Analysis and Recognition, IEEE Computer Society, 2003, pp. 682-682. [pdf]

 

(*) overall number of submissions including private and public ones