ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard
Rui Zhang,Mingkun Yang,Xiang Bai,Baoguang Shi,Dimosthenis Karatzas,Shijian Lu,C. V. Jawahar,Yongsheng Zhou,Qianyi Jiang,Qi Song,Nan Li,Kai Zhou,Lei Wang,Dong Wang,Minghui Liao +14 more
- pp 1577-1581
Reads0
Chats0
TLDR
The ICDAR2019-ReCTS this article, which mainly focuses on reading Chinese text on signboard, has attracted great interest and the final results of the competition are presented in this article.Abstract:
Chinese scene text reading is one of the most challenging problems in computer vision and has attracted great interest. Different from English text, Chinese has more than 6000 commonly used characters and Chinese characters can be arranged in various layouts with numerous fonts. The Chinese signboards in street view are a good choice for Chinese scene text images since they have different backgrounds, fonts and layouts. We organized a competition called ICDAR2019-ReCTS, which mainly focuses on reading Chinese text on signboard. This report presents the final results of the competition. A large-scale dataset of 25,000 annotated signboard images, in which all the text lines and characters are annotated with locations and transcriptions, were released. Four tasks, namely character recognition, text line recognition, text line detection and end-to-end recognition were set up. Besides, considering the Chinese text ambiguity issue, we proposed a multi ground truth (multi-GT) evaluation method to make evaluation fairer. The competition started on March 1, 2019 and ended on April 30, 2019. 262 submissions from 46 teams are received. Most of the participants come from universities, research institutes, and tech companies in China. There are also some participants from the United States, Australia, Singapore, and Korea. 21 teams submit results for Task 1, 23 teams submit results for Task 2, 24 teams submit results for Task 3, and 13 teams submit results for Task 4. The official website for the competition is http://rrc.cvc.uab.es/?ch=12.read more
Citations
More filters
Journal ArticleDOI
RTFN: A robust temporal feature network for time series classification
TL;DR: A novel robust temporal feature network (RTFN) for feature extraction in time series classification, containing a temporal featureNetwork (TFN), a residual structure with multiple convolutional layers, and an LSTM-based attention network (LSTMaN).
Posted Content
Text Recognition in the Wild: A Survey
TL;DR: This literature review attempts to present the entire picture of the field of scene text recognition, which provides a comprehensive reference for people entering this field, and could be helpful to inspire future research.
Posted Content
BoxInst: High-Performance Instance Segmentation with Box Annotations
TL;DR: The core idea is to redesign the loss of learning masks in instance segmentation, with no modification to the segmentation network itself, and demonstrates that the redesigned mask loss can yield surprisingly high-quality instance masks with only box annotations.
Proceedings ArticleDOI
What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels
TL;DR: Recently, Fan et al. as discussed by the authors proposed to train a scene text recognition model with fewer real labels and achieved state-of-the-art performance on scene text classification without synthetic data.
Proceedings ArticleDOI
A Multiplexed Network for End-to-End, Multilingual OCR
Jing Huang,Guan Pang,Rama Kovvuri,Mandy Toh,Kevin J Liang,Praveen Krishnan,Xi Yin,Tal Hassner +7 more
TL;DR: This paper proposed an end-to-end training pipeline that includes both detection and recognition, and achieved state-of-the-art results on both text detection and script identification benchmarks.
References
More filters
Proceedings ArticleDOI
Feature Pyramid Networks for Object Detection
TL;DR: This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.
Proceedings Article
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
TL;DR: In this paper, the authors show that training with residual connections accelerates the training of Inception networks significantly, and they also present several new streamlined architectures for both residual and non-residual Inception Networks.
Posted Content
Feature Pyramid Networks for Object Detection
TL;DR: Feature pyramid networks (FPNets) as mentioned in this paper exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost.
Proceedings ArticleDOI
Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks
TL;DR: This paper presents a novel method for training RNNs to label unsegmented sequences directly, thereby solving both problems of sequence learning and post-processing.
Related Papers (5)
An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition
Baoguang Shi,Xiang Bai,Cong Yao +2 more