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

By Asif Shahab, Faisal Shafait, Andreas R. Dengel. 2011

449 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

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

In Computer Vision and Pattern Recognition

1. Xiang Bai
2. Cong Yao
3. Luc Van Gool
4. Yu Qiao
5. Chunhua Shen
6. Andrew Zisserman
7. Andrea Vedaldi
8. Dacheng Tao

In Evaluation & Benchmarks

1. Xiang Bai
2. Cong Yao
3. Andrew Zisserman
4. Andrea Vedaldi
5. Karen Simonyan
6. Yu Qiao
7. Jiri Matas
8. Lukás Neumann

Citations in the corpus

• Speeding up Convolutional Neural Networks with Low Rank Expansions (2014, background): “The training dataset consists of 163,222 collected character samples from a number of scene text and synthesized character datasets [1, 2, 5, 17, 21, 34, 42].”
• Synthetic Data for Text Localisation in Natural Images (2016, methodology): “SVT is more challenging than the ICDAR data as it contains smaller and lower resolution text.”
• Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition (2014, background): “ICDAR 2013 [13] test dataset contains 1015 groundtruth cropped word images from scene text.”
• Reading Text in the Wild with Convolutional Neural Networks (2014, neutral): “html), ICDAR 2011 (IC11) (Shahab et al. 2011), and ICDAR 2013 (IC13) (Karatzas et al.”
• Large-Lexicon Attribute-Consistent Text Recognition in Natural Images (2012, background): “The results of the entries of the Robust Reading Competition are reproduced from [21].”
• Scene Text Localization and Recognition with Oriented Stroke Detection (2013, methodology): “The proposed method was evaluated on the ICDAR 2011 Robust Reading competition dataset [14], which contains 1189 words and 6393 letters in 255 images.”
• Robust Seed Localization and Growing with Deep Convolutional Features for Scene Text Detection (2015, methodology): “Robust Reading Competition datasets of ICDAR 2011 [15], ICDAR 2013 (Challenge 2: Reading Text in Scene Images) dataset [5] and Street View Text (SVT) [17] dataset.”
• Deep Features for Text Spotting (2014, background): “The four ICDAR datasets – ICDAR 2003 [1], 2005 [28], 2011 [42], and 2013 [24] – containing a varied array of photos of the world that contain scene text.”
• A Unified Framework for Multioriented Text Detection and Recognition (2014, methodology): “We also tested the proposed unified framework on the ICDAR 2011 dataset [33] to evaluate its ability of extracting text information from natural scenes.”
• A robust arbitrary text detection system for natural scene images (2014, methodology): “In summary, we use ICDAR2005, ICDAR2011, MSRA-TD500 and CUTE80 to evaluate the proposed method performance for horizontal, non-horizontal and curved text line detection, respectively.”
• TextBoxes: A Fast Text Detector with a Single Deep Neural Network (2016, unknown): “ICDAR 2011 (IC11) (Shahab, Shafait, and Dengel 2011) There are real-world images with high resolution in the ICDAR 2011 dataset.”
• Detecting Curve Text in the Wild: New Dataset and New Solution (2017, background): “From 2003 on, rectangular labeled datasets such as ICDAR’03 [22], IC-DAR’11 [26], ICDAR’13 [17] and COCO-Text [33] have attracted a great number of research efforts.”
• 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”
• Scene text detection and recognition: recent advances and future trends (2015, methodology): “To address this problem, the organizers of ICDAR 2011 [77] and 2013 [78] adopted the evaluation method proposed by Wolf et al.”
• Scene Text Detection and Recognition: The Deep Learning Era (2018, methodology): “In the ICDAR 2011 and 2013 Robust Reading Competi-tions, previous datasets are modified and extended, which make the new ICDAR 2011 [118] and 2013 [64] datasets.”
• Detecting texts of arbitrary orientations in natural images (2012, background): “Though widely used in the community, the ICDAR datasets [20, 24] only contain horizontal English texts.”