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

Lucas, Simon M.; Panaretos, Alex; Sosa, Luis; Tang, Anthony; Wong, Stephanie E.; Young, R. Michael; Ashida, Kazuki; Nagai, Hiroki; Okamoto, Masayuki; Yamamoto, Hiroaki; Miyao, Hidetoshi; Zhu, Junmin; Ou, Wuwen; Wolf, Christian; Jolion, Jean-Michel; Todoran, Leon; Worring, Marcel; Lin, Xiaofan

doi:10.1007/s10032-004-0134-3

Cited by 251 publications

(107 citation statements)

References 23 publications

Supporting

Mentioning

105

Contrasting

Unclassified

Order By: Relevance

“…We extended the dataset used in earlier Robust Reading Competitions organized in ICDAR 2003 and 2005 [12], [11], [13]. The dataset used in these competitions along with word and character level ground truth in XML format is publicly available at http://algoval.essex.ac.uk/icdar/ Datasets.html.…”

Section: A Datasetmentioning

confidence: 99%

“…Owing to independent input for both tasks, it was allowed to participate in both tasks or in either of them. In contrast to the previous ICDAR Robust Reading Contests [12], [13], both challenges in ICDAR 2011 contest were organized in an open mode. The training and test datasets were made available at specified dates and the participants were given a time frame of three days after the release of the test data to submit their results.…”

Section: The Challengementioning

confidence: 99%

“…To benchmark performance of different scene text segmentation and recognition algorithms, a Robust Reading Competition was organized at ICDAR 2003 [11], [12]. The robust reading problem was divided into three sub-problems, and competitions were run for each stage.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text in Scene Images

Shahab

Shafait

Dengel

2011

2011 International Conference on Document Analysis and Recognition

354

202

View full text Add to dashboard Cite

Abstract-Recognition of text in natural scene images is becoming a prominent research area due to the widespread availablity of imaging devices in low-cost consumer products like mobile phones. To evaluate the performance of recent algorithms in detecting and recognizing text from complex images, the ICDAR 2011 Robust Reading Competition was organized. Challenge 2 of the competition dealt specifically with detecting/recognizing text in natural scene images. This paper presents an overview of the approaches that the participants used, the evaluation measure, and the dataset used in the Challenge 2 of the contest. We also report the performance of all participating methods for text localization and word recognition tasks and compare their results using standard methods of area precision/recall and edit distance.

show abstract

Section: A Datasetmentioning

confidence: 99%

Section: The Challengementioning

confidence: 99%

See 1 more Smart Citation

ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text in Scene Images

Shahab

Shafait

Dengel

2011

2011 International Conference on Document Analysis and Recognition

354

202

View full text Add to dashboard Cite

show abstract

“…There are other datasets employed in this paper. The Robust Reading Dataset from ICDAR2003 (Lucas and et al, 2005) and the Chars74K (de Campos et al, 2009) datasets are selected to be tested as scene images of the English scripts. They contain a total of 17,794 samples of English characters.…”

Section: Datasetsmentioning

confidence: 99%

Object Attention Patches for Text Detection and Recognition in Scene Images using SIFT

Sriman

Schomaker

2015

Proceedings of the International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

Abstract:Natural urban scene images contain many problems for character recognition such as luminance noise, varying font styles or cluttered backgrounds. Detecting and recognizing text in a natural scene is a difficult problem. Several techniques have been proposed to overcome these problems. These are, however, usually based on a bottom-up scheme, which provides a lot of false positives, false negatives and intensive computation. Therefore, an alternative, efficient, character-based expectancy-driven method is needed. This paper presents a modeling approach that is usable for expectancy-driven techniques based on the well-known SIFT algorithm. The produced models (Object Attention Patches) are evaluated in terms of their individual provisory character recognition performance. Subsequently, the trained patch models are used in preliminary experiments on text detection in scene images. The results show that our proposed model-based approach can be applied for a coherent SIFT-based text detection and recognition process.

show abstract

“…Céline Mancas-Thillou Figure 4.4: Differences between a manual text locating system (in red) and an automatic one (in white): some characters may be cut such as the word "SALE" and false detections may appear (bus doors)(Reproduced with kind permission of Springer Science and Business Media from [84]). …”

Section: Db-icdar [1]mentioning

confidence: 99%