mlsanityData to 7 Oct 2026

Scene Text recognition with Full Normalization

arXiv 2109.01034 ↗First posted 13 Jul 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Scene text recognition has made significant progress in recent years and has become an important part of the work-flow. The widespread use of mobile devices opens up wide possibilities for using OCR technologies in everyday life. However, lack of training data for new research in this area remains relevant. In this article, we present a new dataset consisting of real shots on smartphones and demonstrate the effectiveness of profile normalization in this task. In addition, the influence of various augmentations during the training of models for analyzing document images on smartphones is studied in detail. Our dataset is publicly available.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 13 Jul 2021.

Builds on

31 of 44 references.

References · 31

  1. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 519
  2. 2017EAST: An Efficient and Accurate Scene Text Detectorcited by 248
  3. 2014Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognitioncited by 214
  4. 2019Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapescited by 171
  5. 2017Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognitioncited by 161
  6. 2014Reading Text in the Wild with Convolutional Neural Networkscited by 122
  7. 2016Robust Scene Text Recognition with Automatic Rectificationcited by 121
  8. 2016TextBoxes: A Fast Text Detector with a Single Deep Neural Networkcited by 119
  9. 2018TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapescited by 114
  10. 2017Focusing Attention: Towards Accurate Text Recognition in Natural Imagescited by 110
  11. 2018FOTS: Fast Oriented Text Spotting with a Unified Networkcited by 109
  12. 2017ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)cited by 103
19 more
  1. 2018ESIR: End-to-end Scene Text Recognition via Iterative Image Rectificationcited by 79
  2. 2016Recursive Recurrent Nets with Attention Modeling for OCR in the Wildcited by 74
  3. 2018Spatial Fusion GAN for Image Synthesiscited by 68
  4. 2018PixelLink: Detecting Scene Text via Instance Segmentationcited by 60
  5. 2018Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenescited by 44
  6. 2018Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentationcited by 42
  7. 2019GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognitioncited by 37
  8. 2016Multi-Oriented Text Detection with Fully Convolutional Networkscited by 36
  9. 2017Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detectioncited by 31
  10. 2017Single Shot Text Detector with Regional Attentioncited by 31
  11. 2018Accurate Scene Text Detection through Border Semantics Awareness and Bootstrappingcited by 20
  12. 2017WordSup: Exploiting Word Annotations for Character based Text Detectioncited by 14
  13. 2019Scene Text Synthesis for Efficient and Effective Deep Network Trainingcited by 14
  14. 2014Deep Structured Output Learning for Unconstrained Text Recognitioncited by 13
  15. 2019Spatial-Aware GAN for Unsupervised Person Re-identificationcited by 13
  16. 2015Text-Attentional Convolutional Neural Networks for Scene Text Detectioncited by 12
  17. 2020Towards Realistic 3D Embedding via View Alignmentcited by 10
  18. 2014Supervised mid-level features for word image representationcited by 5
  19. 2017WordFence: Text Detection in Natural Images with Border Awarenesscited by 1

Built on by

Not cited yet.