Scene Text Detection and Recognition Paper List

Collect and Record some excellent works on scene text detection and recognition. It will keep updating. If you have any suggestions about how to organize these papers, please contact me !

1. Survey

  • [2018] Scene Text Detection and Recognition: The Deep Learning Era paper
  • [2016-TIP] Text detection, tracking and recognition in video: A comprehensive survey paper
  • [2016-FCS] Scene text detection and recognition: Recent advances and future trends paper
  • [2015-TPMAI] Text detection and recognition in imagery: A survey paper

2. Detection

2.1 Methods

Conventional
  • [2010-CVPR] Detecting text in natural scenes with stroke width transform paper
  • [2012-CVPR] Detecting Texts of Arbitrary Orientations in Natural Images paper
Anchor Based
  • [2018-CVPR] Geometry-Aware Scene Text Detection With Instance Transformation paper code
  • [2018-AAAI] Feature Enhancement Network: A Refined Scene Text Detector paper
  • [2017-AAAI] TextBoxes: A Fast Text Detector with a Single Deep Neural Network paper code
  • [2017-CVPR] Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection paper
  • [2017-ICCV] Single shot text detector with regional attention
  • [2017-ICCV] Deep direct regression for multi-oriented scene text detection
  • [2016-TIP] Text-Attentional Convolutional Neural Networks for Scene Text Detection
  • [2015-CVPR] Symmetry-based text line detection in natural scenes paper
Segmentation Based
  • [2018-ECCV] Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping paper
  • [2018-ECCV] TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes paper
  • [2018-AAAI] PixelLink: Detecting Scene Text via Instance Segmentation papercode
  • [2018] Shape Robust Text Detection with Progressive Scale Expansion Network paper
  • [2017-CVPR] Multi-scale FCN with Cascaded Instance Aware Segmentation for Arbitrary Oriented Word Spotting In The Wild paper
  • [2017-CVPR] EAST: An Efficient and Accurate Scene Text Detector paper code
  • [2017-ICCV] Self-organized Text Detection with Minimal Post-processing via Border Learning paper code
  • [2017-CVPR] Detecting Oriented Text in Natural Images by Linking Segments paper code
  • [2017] Fused Text Segmentation Networks for Multi-oriented Scene Text Detection paper
  • [2016] Scene Text Detection via Holistic, Multi-Channel Prediction paper
  • [2016-CVPR] Multi-Oriented Text Detection with Fully Convolutional Networks paper
  • [2016-CVPR] Accurate text localization in natural image with cascaded convolutional text network paper
Others
  • [2019-AAAI] Scene Text Detection with Supervised Pyramid Context Network paper
  • [2019-WACV] Mask R-CNN with Pyramid Attention Network for Scene Text Detection paper
  • [2018-CVPR] Learning Markov Clustering Networks for Scene Text Detection paper
  • [2016-ECCV] Detecting Text in Natural Image with Connectionist Text Proposal Network paper code

2.2 Specific Targets

Multi-Oriented Text
  • [2018-IJCAI] IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection paper
  • [2018-CVPR] Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation paper
  • [2018-CVPR] Rotation-Sensitive Regression for Oriented Scene Text Detection paper
  • [2017] Arbitrary-oriented scene text detection via rotation proposals paper
  • [2017-CVPR] EAST: An Efficient and Accurate Scene Text Detector paper code
Irregular Text
  • [2018-12] TextField: Learning A Deep Direction Field for Irregular Scene Text Detection paper
  • [2018-11] TextMountain: Accurate Scene Text Detection via Instance Segmentation paper
  • [2018-ECCV] TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes paper
  • [2018-AAAI] PixelLink: Detecting Scene Text via Instance Segmentation papercode
  • [2018] Shape Robust Text Detection with Progressive Scale Expansion Network paper
  • [2017] Detecting Curve Text in the Wild: New Dataset and New Solution paper code
  • [2017] Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition paper code
Long Text
  • [2018-ECCV] TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes paper
  • [2017-CVPR] Detecting Oriented Text in Natural Images by Linking Segments paper code

3. Recognition

3.1 CTC based methods

  • [2017-TPAMI] An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition paper code

3.2 Attention based

  • [2019-AAAI] Scene Text Recognition from Two-Dimensional Perspective paer
  • [2019-11] Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition paper
  • [2018-TPAMI] ASTER: An Attentional Scene Text Recognizer with Flexible Rectification paper code
    • [2018-AAAI] Char-Net: A Character-Aware Neural Network for Distorted Scene Text paper
  • [2018-AAAI] SqueezedText: A Real-time Scene Text Recognition by Binary Convolutional Encoder-decoder Network paper
  • [CVPR-2016] Robust Scene Text Recognition with Automatic Rectification paper

3.3 Others

  • [2019-AAAI] Scene Text Recognition from Two-Dimensional Perspective paper
  • [2018-CVPR] Edit Probability for Scene Text Recognition
  • [2018-CVPR] AON: Towards Arbitrarily-Oriented Text Recognition paper

4. End2End Recognition

  • [2018-ECCV] Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes paper
  • [2018-CVPR] An end-to-end TextSpotter with Explicit Alignment and Attention paper code
  • [2018-CVPR] FOTS: Fast Oriented Text Spotting with a Unified Network paper
  • [2018-AAAI] SEE: Towards Semi-Supervised End-to-End Scene Text Recognition paper
  • [2017-ICCV] Deep TextSpotter: An End-to-End Trainable Scene Text Localization and Recognition Framework paper code
  • [2017-ICCV] Towards end-to-end text spotting with convolutional recurrent neural networks. paper
  • [2018-TIP] TextBoxes++: A Single-Shot Oriented Scene Text Detector. paper code

5. Auxilliary Techs

5.1 Synthetic Data

  • [2018-ECCV] Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes paper
  • [2016-CVPR] Synthetic Data for Text Localisation in Natural Images paper

5.2 Bootstrapping

  • [2018-ECCV] Wordsup: Exploiting word annotations for character based text detection
  • [2017-ICCV] Wetext: Scene text detection under weak supervision

5.3 Context Information

  • [2018-ECCV] Using Object Information for Spotting Text paper

5.4 GAN

  • [2018-ECCV] Synthetically Supervised Feature Learning for Scene Text Recognition paper

6. Unsorted

  • [2018-09] TextContourNet: a Flexible and Effective Framework for Improving Scene Text Detection Architecture with a Multi-task Cascade paper
  • [2018-10] Correlation Propagation Networks for Scene Text Detection paper

There are also other helpful resources:

请作者吃酒!