Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition

@article{Chng2017TotalTextAC,
  title={Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition},
  author={Chee-Kheng Chng and Chee Seng Chan},
  journal={2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)},
  year={2017},
  volume={01},
  pages={935-942}
}
  • Chee-Kheng Chng, Chee Seng Chan
  • Published 2017
  • Computer Science
  • 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)
Text in curve orientation, despite being one of the common text orientations in real world environment, has close to zero existence in well received scene text datasets such as ICDAR'13 and MSRA-TD500. The main motivation of Total-Text is to fill this gap and facilitate a new research direction for the scene text community. On top of conventional horizontal and multi-oriented text, it features curved-oriented text. Total-Text is highly diversified in orientations, more than half of its images… Expand
Total-Text: toward orientation robustness in scene text detection
TLDR
A new scene text detection model is proposed as the baseline for Total-Text, namely Polygon-Faster-RCNN, and its ability to detect text of all orientations is demonstrated. Expand
TextPolar: irregular scene text detection using polar representation
TLDR
A segmentation-based method, TextPolar, for irregular scene text detection by using a novel text representation that predicts the text center line via pixel-level segmentation and adopts polar coordinates instead of Euclidean coordinates to precisely depict the contour of text regions. Expand
SA-Text: Simple but Accurate Detector for Text of Arbitrary Shapes
TLDR
A pipeline-based text spotting system called SAA is proposed, which outperforms four state-of-the-art text spotting frameworks by at least 9 percent points in the F-measure, which means that SA-Text can be used as a complete text detection and recognition system in real applications. Expand
TextField: Learning a Deep Direction Field for Irregular Scene Text Detection
TLDR
A novel text detector named TextField, which outperforms the state-of-the-art methods by a large margin on two curved text datasets: Total-Text and SCUT-CTW1500, respectively; TextField also achieves very competitive performance on multi-oriented datasets: ICDAR 2015 and MSRA-TD500. Expand
Irregular scene text detection via attention guided border labeling
TLDR
A novel method to detect irregular scene texts based on instance-aware segmentation based on an attention guided semantic segmentation model to precisely label the weighted borders of text regions is proposed. Expand
CentripetalText: An Efficient Text Instance Representation for Scene Text Detection
TLDR
An efficient text instance representation named CentripetalText (CT) is proposed, which decomposes text instances into the combination of text kernels and centripetals, and outperforms Mask TextSpotter v3 by 1.1% on Total-Text and end-to-end scene text recognition. Expand
AB-LSTM
TLDR
An Attention-based Bidirectional Long Short-Term Memory (AB-LSTM) model for scene text detection is proposed and results demonstrate that the proposed method can achieve competitive results, and well handle scene text objects with arbitrary shapes. Expand
IoU-Related Arbitrary Shape Text Scoring Detector
TLDR
The proposed method replaces the original $\ell _{1}$ -smooth loss with the proposed IoU-related loss and adds a text scoring branch to align the confidence score with the text mask IoU to make the model highly relevant to IoU, achieving the goal of improving detection performance by improving IoU directly in a simple but effective way. Expand
MSR: Multi-Scale Shape Regression for Scene Text Detection
TLDR
The proposed MSR detects scene texts by predicting dense text boundary points that inherently capture the location and shape of text lines accurately and are also more tolerant to the variation of text line length as compared with the state of the arts using proposals or segmentation. Expand
ContourNet: Taking a Further Step Toward Accurate Arbitrary-Shaped Scene Text Detection
TLDR
The ContourNet is proposed, which effectively handles the problems taking a further step toward accurate arbitrary-shaped text detection and suppresses false positives by only outputting predictions with high response value in both orthogonal directions. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 25 REFERENCES
COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
TLDR
The COCO-Text dataset is described, which contains over 173k text annotations in over 63k images and presents an analysis of three leading state-of-the-art photo Optical Character Recognition (OCR) approaches on the dataset. Expand
Scene Text Detection via Holistic, Multi-Channel Prediction
TLDR
This work proposes to localize text in a holistic manner, by casting scene text detection as a semantic segmentation problem, and demonstrates that the proposed algorithm substantially outperforms previous state-of-the-art approaches. Expand
A robust arbitrary text detection system for natural scene images
TLDR
A robust system based on the concepts of Mutual Direction Symmetry (MDS), Mutual Magnitude Symmetric (MMS) and Gradient Vector Symmeter (GVS) properties to identify text pixel candidates regardless of any orientations including curves from natural scene images is presented. Expand
Robust Text Detection in Natural Scene Images
TLDR
An accurate and robust method for detecting texts in natural scene images using a fast and effective pruning algorithm to extract Maximally Stable Extremal Regions (MSERs) as character candidates using the strategy of minimizing regularized variations is proposed. Expand
Detecting Oriented Text in Natural Images by Linking Segments
TLDR
SegLink, an oriented text detection method to decompose text into two locally detectable elements, namely segments and links, achieves an f-measure of 75.0% on the standard ICDAR 2015 Incidental (Challenge 4) benchmark, outperforming the previous best by a large margin. Expand
Text Localization in Natural Images Using Stroke Feature Transform and Text Covariance Descriptors
TLDR
A powerful low-level filter called the Stroke Feature Transform (SFT) is proposed, which extends the widely-used Stroke Width Transform (SWT) by incorporating color cues of text pixels, leading to significantly enhanced performance on inter-component separation and intra-component connection. Expand
Multi-Orientation Scene Text Detection with Adaptive Clustering
TLDR
A unified distance metric learning framework for adaptive hierarchical clustering, which can simultaneously learn similarity weights and the clustering threshold, and an effective multi-orientation scene text detection system, which constructs text candidates by grouping characters based on this adaptive clustering. Expand
Multi-oriented Text Detection with Fully Convolutional Networks
TLDR
A novel approach for text detection in natural images that consistently achieves the state-of-the-art performance on three text detection benchmarks: MSRA-TD500, I CDAR2015 and ICDAR2013. Expand
Scene Text Localization and Recognition with Oriented Stroke Detection
TLDR
The method introduces a novel approach for character detection and recognition which combines the advantages of sliding-window and connected component methods and efficiently calculated a novel character representation efficiently calculated from the values obtained in the stroke detection phase. Expand
Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network
TLDR
A novel Cascaded Convolutional Text Network (CCTN) is proposed that joints two customized convolutional networks for coarse-to-fine text localization and exhibits surprising robustness and discriminative power. Expand
...
1
2
3
...