ICDAR 2015 competition on Robust Reading
Dìmosthenis Karatzasa b, Lluís Gómeza b, Anguelos Nicolaoua b, Suman K. Ghosha b, Andrew D. Bagdanova b, Masakazu Iwamurac d, Jiřı́ Matase f, Lukáš Neumanne f, Vijay Chandrasekharg h, Shijian Lug h, Faisal Shafait Bi j, Seiichi Uchidak, Ernest Valvenya b
- aComputer Vision Centre, Universitat Autònoma de Barcelona
- bComputer Vision Centre, Universitat Autonoma de Barcelona, Spain
- cOsaka Prefecture University, Japan
- dOsaka Prefecture University, JAPAN#TAB#
- eCzech Technical University in Prague, Czech Republic
- fCzech Technical Univ in Prague (Czech Republic)
- gInstitute for Infocomm Research, Singapore
- hInst. for Infocomm Res., Singapore
- iNational university of of Science and Technology (NUST), Pakistan
- jNational University of Science and Technology (NUST), Pakistan
- kKyushu University, Japan
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
Results of the ICDAR 2015 Robust Reading Competition are presented. A new Challenge 4 on Incidental Scene Text has been added to the Challenges on Born-Digital Images, Focused Scene Images and Video Text. Challenge 4 is run on a newly acquired dataset of 1,670 images evaluating Text Localisation, Word Recognition and End-to-End pipelines. In addition, the dataset for Challenge 3 on Video Text has been substantially updated with more video sequences and more accurate ground truth data. Finally, tasks assessing End-to-End system performance have been introduced to all Challenges. The competition took place in the first quarter of 2015, and received a total of 44 submissions. Only the tasks newly introduced in 2015 are reported on. The datasets, the ground truth specification and the evaluation protocols are presented together with the results and a brief summary of the participating methods.