ICDAR 2005 text locating competition results

By Simon M. M. Lucas. 2005

322 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

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 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.”
• A Hybrid Approach to Detect and Localize Texts in Natural Scene Images (2011, methodology): “We evaluated the performance of the proposed approach on a public dataset: ICDAR 2005 text locating competition dataset [23], and a multilingual image dataset collected by us.”
• Detecting texts of arbitrary orientations in natural images (2012, methodology): “Although widely used in the community, the ICDAR dataset [21, 20] has two major drawbacks.”
• Scene text detection and recognition: recent advances and future trends (2015, methodology): “The ICDAR competitions [43, 76–78] also include text recognition tasks.”
• Multi-oriented Text Detection with Fully Convolutional Networks (2016, background): “The evaluation protocol of this dataset inherits from [14].”
• 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.”
• Text String Detection from Natural Scenes by Structure-based Partition and Grouping (2011, methodology): “To evaluate the performance, we calculate two metrics, precision and recall as in [21], [22].”
• 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.”
• Scene Text Detection and Recognition: The Deep Learning Era (2018, methodology): “The dataset is also used in ICDAR 2005 Text Locating Competition [86].”
• Symmetry-based text line detection in natural scenes (2015, methodology): “The datasets used in ICDAR 2011(2) and 2013(3) are inherited from the benchmark used in the previous ICDAR competitions [21, 20], but have undergone extension and modification, since there are some problems with the previous dataset (e.”
• A Unified Framework for Multioriented Text Detection and Recognition (2014, methodology): “The ICDAR 2011 dataset [33] is an extension to the dataset used for the text locating competitions of ICDAR 2003 [65] and 2005 [66].”
• Robust text detection in natural images with edge-enhanced Maximally Stable Extremal Regions (2011, methodology): “Shivakumara et al. extract CCs by performing K-means clustering in the Fourier-Laplacian domain, and eliminate false positives by using text straightness and edge density [17].”
• ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text in Scene Images (2011, methodology): “The text locating problem received five entries, whereas no one participated in the character recognition and word recognition problem.”