ICDAR 2003 robust reading competitions

By Simon M. M. Lucas, A. Panaretos, Luis Sosa, Anthony Tang, Shirley Wong, Robert Young, R. Young. 2003

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

In Evaluation & Benchmarks

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

Citations in the corpus

• Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition (2014, methodology): “Second, we consider the standard benchmarks IC03 [16], SVT [26], and IC13 [13], which contain natural scene images, but cover smaller word lexicons.”
• Reading Text in the Wild with Convolutional Neural Networks (2014, methodology): “Shahab, A., Shafait, F., Dengel, A.: ICDAR 2011 robust reading competition challenge 2: Reading text in scene images.”
• COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images (2016, methodology): “We analyze COCO-Text and compare it to other popular scene text datasets, in particular, with ICDAR 03 [11] and ICDAR 15 [9].”
• End-to-End Text Recognition with Hybrid HMM Maxout Models (2013, methodology): “We test our word recognition subsystem on word images from the ICDAR 2003 (Lucas et al., 2003) and SVT (Wang & Belongie, 2010) word recognition test sets.”
• ICDAR 2005 text locating competition results (2005, methodology): “2003 competition [5], based on the notions of precision and recall, as used by the information retrieval community.”
• Text Localization in Real-World Images Using Efficiently Pruned Exhaustive Search (2011, methodology): “The standard evaluation protocol defined in [13] was used.”
• Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes (2018, background): “ICDAR 2003 (IC03) is cropped and filtered from [49].”
• What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis (2019, background): “SVT consists of 257 images for training and 647 images for evaluation, • ICDAR2003 (IC03) [19] was created for the ICDAR 2003 Robust Reading competition for reading camera- captured scene texts.”
• Object count/area graphs for the evaluation of object detection and segmentation algorithms (2006, methodology): “problem the authors themselves report in [ 13 ].”
• Text Detection and Character Recognition in Scene Images with Unsupervised Feature Learning (2011, methodology): “In particular, we have compiled our training data from the ICDAR 2003 training images [27], Weinman et al.”
• Text Detection and Recognition in Imagery: A Survey (2015, methodology): “(2003) [21] Scene text Camera D/R 509 (258/251) 2,276”
• Robust Seed Localization and Growing with Deep Convolutional Features for Scene Text Detection (2015, methodology): “We evaluated our method on several public datasets, including ICDAR 2003 Text Locating Competition dataset [8], by us that applies SVM on hand-crafted features extracted from MSERs, ’Geometric’ refers to only the geometric conformity being considered in computing associative quality score, while…”
• Robust text detection in natural images with edge-enhanced Maximally Stable Extremal Regions (2011, methodology): “As a primary test we use the well-known ICDAR text detection competition data set [26, 15], which was also used as a benchmark for [16, 27, 28].”
• Reading Scene Text in Deep Convolutional Sequences (2015, methodology): “periments and Results The experiments were conducted on three standard benchmarks for cropped word image recognition: the Street View Text (SVT) (Wang, Babenko, and Belongie 2011), ICDAR 2003 (IC03) (Lucas et al. 2003) and IIIT 5K-word (IIIT5K) (Mishra., Alahari, and Jawahar 2012). The SVT has 647 w”
• Object Detection in 20 Years: A Survey (2019, background): “ICDAR [71] 2003 ICDAR2003 is one of the first public datasets for text detection.”
• Detecting and reading text in natural scenes (2004, background): “More relevant work is reported in [8], [9], [10], [22] ,[23]. In particular, Lucas et al [ 10 ] report on”