Research map / Detection and segmentation / CNN features
Deep TextSpotter: An End-To-End Trainable Scene Text Localization and Recognition Framework
Michal Busta, Lukas Neumann, Jiri Matas
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 |
|---|---|---|---|
| train detection and recognition jointly instead of combining separately trained localization and recognition methods | Deep TextSpotter · ICDAR 2013 end-to-end | f-measure: by at least 3 per cent points on every measure | Improved |
| use one fully convolutional end-to-end pipeline instead of separate localization plus recognition stages | Deep TextSpotter · ICDAR 2013 end-to-end | speed: more than 20 times faster than Gupta et al. | Improved |
| use the end-to-end pipeline on ICDAR 2015 instead of the best published method | Deep TextSpotter · ICDAR 2015 end-to-end | speed: 45 times faster than Gomez et al. | Improved |
Later papers that compared with this method
3 later accepted papers report DeepTextSpotter as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting (AAAI 2020 · better on 1 of 1 shared result)
- An End-to-End TextSpotter With Explicit Alignment and Attention (CVPR 2018 · better on 3 of 3 shared results)
- Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes (ECCV 2018 · better on 3 of 3 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
- TextBoxes: A Fast Text Detector with a Single Deep Neural Network (AAAI 2017 · similarity 0.90)
- 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 0.89)
- An End-to-End TextSpotter With Explicit Alignment and Attention (CVPR 2018 · similarity 0.89)
- Towards End-To-End Text Spotting With Convolutional Recurrent Neural Networks (ICCV 2017 · similarity 0.89)
- Scene Text Detection and Recognition: The Deep Learning Era (IJCV 2020 · similarity 0.89)
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.
