2017

Detecting Curve Text in the Wild: New Dataset and New Solution

Yuliang, Liu, Lianwen, Jin, Shuaitao, Zhang et al.

Understand

Scene text detection has been made great progress in recent years.

The detection manners are evolving from axis-aligned rectangle to rotated rectangle and further to quadrangle.
However, current datasets contain very little curve text, which can be widely observed in scene images such as signboard, product name and so on.
To raise the concerns of reading curve text in the wild, in this paper, we construct a curve text dataset named CTW1500, which includes over 10k text annotations in 1,500 images (1000 for training and 500 for testing).

Built on

Long short-term memory
S. Hochreiter and J. Schmidhuber · 1997
Earlier work this paper cites.
Icdar 2003 robust reading competitions
S. M. Lucas, A. Panaretos, L. Sosa, A. Tang, S. Wong, and R. Young · 2003
Earlier work this paper cites.
Detecting and reading text in natural scenes
X. Chen and A. L. Yuille · 2004
Earlier work this paper cites.
Efficient non-maximum suppression
A. Neubeck and L. V. Gool · 2006
Earlier work this paper cites.
Imagenet: A large-scale hierarchical image database
J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei · 2009
Earlier work this paper cites.
Detecting text in natural scenes with stroke width transform
B. Epshtein, E. Ofek, and Y. Wexler · 2010
Earlier work this paper cites.
The pascal visual object classes (voc) challenge
M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman · 2010
Earlier work this paper cites.
Word spotting in the wild
K. Wang and S. Belongie · 2010
Earlier work this paper cites.
Neocr: A configurable dataset for natural image text recognition
R. Nagy, A. Dicker, and K. Meyer-Wegener · 2011
Earlier work this paper cites.
Icdar 2011 robust reading competition challenge 2: Reading text in scene images
A. Shahab, F. Shafait, and A. Dengel · 2011
Earlier work this paper cites.
Text string detection from natural scenes by structure-based partition and grouping
C. Yi and Y. Tian · 2011
Earlier work this paper cites.
Detecting texts of arbitrary orientations in natural images
C. Yao, X. Bai, W. Liu, and Y. Ma · 2012
Earlier work this paper cites.
Icdar 2013 robust reading competition
D. Karatzas, F. Shafait, S. Uchida, M. Iwamura, L. G. I. Bigorda, S. R. Mestre, J. Mas, D. F. Mota, J. A. Almazàn, and L. P. D. L. Heras · 2013
Earlier work this paper cites.

Similar

Caffe: Convolutional architecture for fast feature embedding
Y. Jia and e. a. Shelhamer, Evan · 2014
Cited alongside, same era.
Very deep convolutional networks for large-scale image recognition
Original
K. Simonyan and A. Zisserman · 2014
Cited alongside, same era.
Icdar 2015 competition on robust reading
D. Karatzas and e. a. Gomez-Bigorda, Lluis · 2015
Cited alongside, same era.
Faster r-cnn: Towards real-time object detection with region proposal networks
S. Ren, K. He, R. Girshick, and J. Sun · 2015
Cited alongside, same era.
Multi-orientation scene text detection with adaptive clustering
X. C. Yin, W. Y. Pei, J. Zhang, and H. W. Hao · 2015
Cited alongside, same era.
R-fcn: Object detection via region-based fully convolutional networks
J. Dai, Y. Li, K. He, and J. Sun · 2016
Cited alongside, same era.
Deep residual learning for image recognition
K. He, X. Zhang, S. Ren, and J. Sun · 2016
Cited alongside, same era.
Recursive recurrent nets with attention modeling for ocr in the wild
C.-Y. Lee and S. Osindero · 2016
Cited alongside, same era.
An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition
B. Shi, X. Bai, and C. Yao · 2016
Cited alongside, same era.
Robust scene text recognition with automatic rectification
B. Shi, X. Wang, P. Lyu, C. Yao, and X. Bai · 2016
Cited alongside, same era.
Detecting text in natural image with connectionist text proposal network
Z. Tian, W. Huang, T. He, P. He, and Y. Qiao · 2016
Cited alongside, same era.
Coco-text: Dataset and benchmark for text detection and recognition in natural images
Original
A. Veit and e. a. Matera, Tomas · 2016
Cited alongside, same era.

Then

Fused text segmentation networks for multi-oriented scene text detection
Original
Y. Dai, Z. Huang, Y. Gao, and K. Chen · 2017
Closest in time.
Mask r-cnn
K. He, G. Gkioxari, P. Dollár, and R. Girshick · 2017
Closest in time.
Deep direct regression for multi-oriented scene text detection
W. He, X.-Y. Zhang, F. Yin, and C.-L. Liu · 2017
Closest in time.
Wordsup: Exploiting word annotations for character based text detection
H. Hu, C. Zhang, Y. Luo, Y. Wang, J. Han, and E. Ding · 2017
Closest in time.
“icdar2017 robust reading competition – challenge on multi-lingual scene text detection and script identification” [online]
e. a. I, Bizid · 2017
Closest in time.
“icdar 2017 robust reading challenge on omnidirectional video” [online]
M. T. M. N. S. H. I. Y. K. K. e. a. Iwamura, M · 2017
Closest in time.
Openimages: A public dataset for large-scale multi-label and multi-class image classification
I. Krasin and e. a. Duerig, Tom · 2017
Closest in time.
Towards end-to-end text spotting with convolutional recurrent neural networks
Original
H. Li, P. Wang, and C. Shen · 2017
Closest in time.
Deep matching prior network: Toward tighter multi-oriented text detection
Y. Liu and L. Jin · 2017
Closest in time.
Detecting oriented text in natural images by linking segments
B. Shi, X. Bai, and S. Belongie · 2017
Closest in time.
Icdar2017 competition on reading chinese text in the wild (rctw-17)
Original
B. Shi, Yao, M. Liao, Y. M., X. P., L. Cui, L. S. Serge Belongie, and B. X · 2017
Closest in time.
East: An efficient and accurate scene text detector
X. Zhou, C. Yao, H. Wen, Y. Wang, S. Zhou, W. He, and J. Liang · 2017
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…