TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes

By Shangbang Long, J. Ruan, W. Zhang, Xin He, Cong Yao. European Conference on Computer Vision, 2018

588 citations recorded by the source corpus.

Driven by deep neural networks and large scale datasets, scene text detection methods have progressed substantially over the past years, continuously refreshing the performance records on various standard benchmarks. However, limited by the representations (axis-aligned rectangles, rotated rectangles or quadrangles) adopted to describe text, existing methods may fall short when dealing with much more free-form text instances, such as curved text, which are actually very common in real-world scenarios. To tackle this problem, we propose a more flexible representation for scene text, termed as TextSnake, which is able to effectively represent text instances in horizontal, oriented and curved forms. In TextSnake, a text instance is described as a sequence of ordered, overlapping disks centered at symmetric axes, each of which is associated with potentially variable radius and orientation. Such geometry attributes are estimated via a Fully Convolutional Network (FCN) model. In experiments, the text detector based on TextSnake achieves state-of-the-art or comparable performance on Total-Text and SCUT-CTW1500, the two newly published benchmarks with special emphasis on curved text in natural images, as well as the widely-used datasets ICDAR 2015 and MSRA-TD500. Specifically, TextSnake outperforms the baseline on Total-Text by more than 40% in F-measure.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/8d4bbfc2d83088d649756f6bac554bd59c17f6e9

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. Chunhua Shen
2. Xiang Bai
3. Cong Yao
4. Luc Van Gool
5. Yu Qiao
6. Dacheng Tao
7. Alan L. Yuille
8. Ming-Hsuan Yang

In Media Technology

1. Cong Yao
2. Xiang Bai
3. Xin He
4. Minghui Liao
5. Shangbang Long
6. Zhaoyi Wan
7. Pengyuan Lyu
8. Chunhua Shen

Citations in the corpus

• Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation (2019, methodology): “Scale Speed TextSnake [19] 768 1.1 fps Mask Textspotter [20] 720 6.9 fps Proposed 720 10.0 fps Table 9.”
• Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes (2018, methodology): “Note that although [48] reported detection results on Total-Text, it used a different evaluation protocol.”
• Scene Text Detection and Recognition: The Deep Learning Era (2018, background): “Viewing the problem from a different perspective, Long et al. [85] argues that text can be represented as a series of sliding round disks along the text center line (TCL), which accord with the running direction of the text instance, as shown in Fig.7.”
• Real-time Scene Text Detection with Differentiable Binarization (2019, methodology): “TextSnake (Long et al. 2018) 82.7 74.5 78.4 - ATRR (Wang et al. 2019b) 80.9 76.2 78.5 - MTS (Lyu et al. 2018a) 82.5 75.6 78.6 - TextField (Xu et al. 2019) 81.2 79.9 80.6 - LOMO (Zhang et al. 2019)* 87.6 79.3 83.3 - CRAFT (Baek et al. 2019) 87.6 79.9 83.6 - CSE (Liu et al. 2019b) 81.4 79.1 80.2 -…”
• Shape Robust Text Detection With Progressive Scale Expansion Network (2018, methodology): “Recently, TextSnake [26] used ordered disks to represent curve text for curve text detection.”
• Character Region Awareness for Text Detection (2019, background): “Recently, scene text detectors based on deep learning have shown promising performance [8, 40, 21, 4, 11, 10, 12, 13, 17, 24, 25, 32, 26].”
• ABCNet: Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network (2020, methodology): “Compared to segmentation-based methods [41, 46, 1, 39, 47, 29], regression-based methods are more direct solutions to oriented or curved text detection, e.”
• Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes (2019, methodology): “Segmentation-based methods [40, 35, 21, 13] mainly draw inspiration from semantic segmentation methods and regard all the pixels within text bounding boxes as positive regions.”
• Symmetry-Constrained Rectification Network for Scene Text Recognition (2019, background): “[33] adopt local geometrical attributes, to represent the text shape for scene text detection.”
• Confidence-aware Non-repetitive Multimodal Transformers for TextCaps (2020, unknown): “Another method is based on segmentation (Long et al. 2018).”
• Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation Network (2019, methodology): “Arbitrary-shaped text detection, one of the most challenging tasks in text detection, is receiving more and more research attention Some new methods [31, 35, 49, 24] have been put forward to detect curve text instance.”