Research map / Detection and segmentation / CNN features
TextBoxes: A Fast Text Detector with a Single Deep Neural Network
Minghui Liao, Baoguang Shi, Xiang Bai, Xinggang Wang, Wenyu Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add multiple rescaled input scales (ablation) | TextBoxes · ICDAR 2013 | F-measure: 0.80 -> 0.85 | Improved |
| use the fast single-scale implementation instead of the full TextBoxes configuration (ablation) | TextBoxes · ICDAR 2013, IC13 Eval | F-measure: 0.85 -> 0.80 | Hurt |
| use the fast single-scale implementation instead of the full TextBoxes configuration (ablation) | TextBoxes · ICDAR 2013, DetEval | F-measure: 0.86 -> 0.81 | Hurt |
| add recognition-based scoring to detection candidates | TextBoxes · Word spotting | F-measure | Improved |
Later papers that compared with this method
8 later accepted papers report TextBoxes++ as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.
- Towards End-to-End Text Spotting in Natural Scenes (TPAMI 2021 · better on 4 of 6 shared results)
- Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection (IJCV 2021 · better on 2 of 2 shared results)
- Accurate Structured-Text Spotting for Arithmetical Exercise Correction (AAAI 2020 · better on 3 of 3 shared results)
- DeRPN: Taking a Further Step toward More General Object Detection (AAAI 2019 · better on 1 of 1 shared result)
- Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes (ECCV 2018 · better on 3 of 3 shared results)
- FOTS: Fast Oriented Text Spotting With a Unified Network (CVPR 2018 · better on 0 of 2 shared results)
- Towards End-To-End Text Spotting With Convolutional Recurrent Neural Networks (ICCV 2017 · better on 5 of 6 shared results)
- Single Shot Text Detector With Regional Attention (ICCV 2017 · better on 3 of 4 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Deep TextSpotter: An End-To-End Trainable Scene Text Localization and Recognition Framework (ICCV 2017 · similarity 0.90)
- Towards End-To-End Text Spotting With Convolutional Recurrent Neural Networks (ICCV 2017 · similarity 0.89)
- Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes (ECCV 2018 · similarity 0.89)
- EAST: An Efficient and Accurate Scene Text Detector (CVPR 2017 · similarity 0.88)
- DeepSolo: Let Transformer Decoder With Explicit Points Solo for Text Spotting (CVPR 2023 · similarity 0.88)
- Scene Text Detection and Recognition: The Deep Learning Era (IJCV 2020 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
