mlsanityData to 14 Oct 2026

Detecting Oriented Text in Natural Images by Linking Segments

arXiv 1703.06520 ↗First posted 19 Mar 2017cs.CVcited by 80

Not on the map. Why?

Abstract (arXiv)

Most state-of-the-art text detection methods are specific to horizontal Latin text and are not fast enough for real-time applications. We introduce Segment Linking (SegLink), an oriented text detection method. The main idea is to decompose text into two locally detectable elements, namely segments and links. A segment is an oriented box covering a part of a word or text line; A link connects two adjacent segments, indicating that they belong to the same word or text line. Both elements are detected densely at multiple scales by an end-to-end trained, fully-convolutional neural network. Final detections are produced by combining segments connected by links. Compared with previous methods, SegLink improves along the dimensions of accuracy, speed, and ease of training. It achieves an f-measure of 75.0% on the standard ICDAR 2015 Incidental (Challenge 4) benchmark, outperforming the previous best by a large margin. It runs at over 20 FPS on 512x512 images. Moreover, without modification, SegLink is able to detect long lines of non-Latin text, such as Chinese.

Key facts. Cited by 80 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 29; 2022: 20; 2023: 14; 2024: 13; 2025: 4.

80 papers.

Sort:

By area:

  1. 2022Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusioncited by 94
  2. 2021ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spottingcited by 84
  3. 2021Fourier Contour Embedding for Arbitrary-Shaped Text Detectioncited by 80
  4. 2023UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understandingcited by 74
  5. 2023SPTS v2: Single-Point Scene Text Spottingcited by 66
  6. 2021PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Textcited by 65
  7. 2022Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detectioncited by 65
  8. 2021Adaptive Boundary Proposal Network for Arbitrary Shape Text Detectioncited by 47
  9. 2023Turning a CLIP Model into a Scene Text Detectorcited by 44
  10. 2021MOST: A Multi-Oriented Scene Text Detector with Localization Refinementcited by 33
  11. 2021Towards Real-world X-ray Security Inspection: A High-Quality Benchmark and Lateral Inhibition Module for Prohibited Items Detectioncited by 30
  12. 2022Arbitrary Shape Text Detection via Boundary Transformercited by 28
38 more
  1. 2021PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyondcited by 27
  2. 2022Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spottingcited by 27
  3. 2021TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representationcited by 26
  4. 2021Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detectioncited by 23
  5. 2021Stroke-Based Scene Text Erasing Using Synthetic Data for Trainingcited by 20
  6. 2023Modeling Entities as Semantic Points for Visual Information Extraction in the Wildcited by 20
  7. 2022Vision-Language Pre-Training for Boosting Scene Text Detectorscited by 18
  8. 2022Kernel Proposal Network for Arbitrary Shape Text Detectioncited by 17
  9. 2021Industrial Scene Text Detection with Refined Feature-attentive Networkcited by 16
  10. 2022Arbitrary Shape Text Detection via Segmentation with Probability Mapscited by 15
  11. 2021I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detectioncited by 14
  12. 2021CentripetalText: An Efficient Text Instance Representation for Scene Text Detectioncited by 13
  13. 2023Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learningcited by 12
  14. 2022Text Growing on Leafcited by 11
  15. 2021Video Text Tracking With a Spatio-Temporal Complementary Modelcited by 10
  16. 2024ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spottingcited by 10
  17. 2021FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representationcited by 9
  18. 2023Turning a CLIP Model into a Scene Text Spottercited by 9
  19. 2023Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectorscited by 9
  20. 2023Hierarchical Text Spotter for Joint Text Spotting and Layout Analysiscited by 8
  21. 2024Seeing Text in the Dark: Algorithm and Benchmarkcited by 8
  22. 2021All You Need is a Second Look: Towards Arbitrary-Shaped Text Detectioncited by 7
  23. 2022Graph Fusion Network for Multi-Oriented Object Detectioncited by 7
  24. 2022Zoom Text Detectorcited by 7
  25. 2023DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spottingcited by 7
  26. 2022Arbitrary Shape Text Detection using Transformerscited by 6
  27. 2022TRIE++: Towards End-to-End Information Extraction from Visually Rich Documentscited by 6
  28. 2022Contextual Text Block Detection towards Scene Text Understandingcited by 6
  29. 2022CBNet: A Plug-and-Play Network for Segmentation-Based Scene Text Detectioncited by 6
  30. 2021Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Linkscited by 5
  31. 2021Plot2Spectra: an Automatic Spectra Extraction Toolcited by 5
  32. 2021CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoningcited by 4
  33. 2022OCR-RTPS: An OCR-based real-time positioning system for the valet parkingcited by 4
  34. 2022A Comprehensive Gold Standard and Benchmark for Comics Text Detection and Recognitioncited by 4
  35. 2024EAFormer: Scene Text Segmentation with Edge-Aware Transformerscited by 4
  36. 2024Spotlight Text Detector: Spotlight on Candidate Regions Like a Cameracited by 4
  37. 2023PBFormer: Capturing Complex Scene Text Shape with Polynomial Band Transformercited by 3
  38. 2024Real-Time Text Detection with Similar Mask in Traffic, Industrial, and Natural Scenescited by 3

50 most cited of 80 All 80 (JSON)