ICDAR 2003 robust reading competitions: entries, results, and future directions

By Simon M. M. Lucas, A. Panaretos, Luis Sosa, Anthony Tang, Shirley Wong, Robert Young, Kazuki Ashida, Hiroki Nagai, Masayuki Okamoto, Hiroaki Yamamoto and 8 more. International Journal of Document Analysis and Recognition (IJDAR), 2005

309 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/e2ee104b00d45161f48d8760ec9955452944f2cf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Cong Yao
2. Xiang Bai
3. Baoguang Shi
4. Minghui Liao
5. Shangbang Long
6. Mingkun Yang
7. Pengyuan Lyu
8. Qixiang Ye

Citations in the corpus

• ASTER: An Attentional Scene Text Recognizer with Flexible Rectification (2019, background): “ICDAR 2003 (IC03) [42] contains 860 images of cropped word after filtering.”
• Text Detection and Recognition in Imagery: A Survey (2015, background): “THE problems of text detection and recognition in images and video have received increased attention in recent years, as indicated by the emergence of recent ”robust reading” competitions in 2003, 2005, 2011, and 2013 [21], [43], [44], [144], along with bi-annual international workshops on camera-ba”
• ICDAR 2005 text locating competition results (2005, background): “In [6], the results remain very similar under the new measure, however, so despite the limitations of our simple measure, this is the one we still use to rank the entries.”
• ICDAR 2015 competition on Robust Reading (2015, background): “The competition dates back to 2003[1] [2] [3], and was substantially revised in 2011 and 2013 [4] [5] [6], creating a comprehensive reference framework for robust reading pipelines evaluation [7].”
• ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text in Scene Images (2011, methodology): “In contrast to the previous ICDAR Robust Reading Contests [12], [13], both challenges in ICDAR 2011 contest were organized in an open mode.”
• text Detection with Convolutional Neural Networks (2008, methodology): “System Precision Recall f Detected HWDavid 0.43 0.52 0.47 1916 Ashida 0.53 0.41 0.46 1515 Wolf 0.21 0.52 0.30 3477 Todoran 0.14 0.18 0.16 1368 ConvNN 0.54 0.61 0.57 751 for an exact definition).”
• An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition (2015, background): “IC03 [30] test dataset contains 251 scene images with labeled text bounding boxes.”