Research map / Detection and segmentation / CNN features
Convolutional Character Networks
Linjie Xing, Zhi Tian, Weilin Huang, Matthew R. Scott
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 iterative character detection on real images (ablation) | CharNet R-50 · ICDAR 2015 detection | F-measure: 65.38 -> 89.70 | Improved |
| add iterative character detection on real images (ablation) | CharNet R-50 · ICDAR 2015 E2E | F-measure: 33.69 -> 62.18 | Improved |
| add iterative character detection on real images (ablation) | CharNet H-57 · ICDAR 2015 E2E | F-measure: 39.43 -> 66.92 | Improved |
| add iterative character detection on real images (ablation) | CharNet H-88 · ICDAR 2015 E2E | F-measure: 39.94 -> 69.14 | Improved |
| add iterative character detection on real images (ablation) | CharNet H-88 · ICDAR 2015 detection | F-measure: 65.11 -> 90.97 | Improved |
| first iteration on real images (step 0 to 1) (ablation) | CharNet · Total-Text E2E | F-measure: 39.3 -> 62.9 | Improved |
| more iterative steps (step 1 to 3) (ablation) | CharNet · Total-Text E2E | F-measure: 62.9 -> 66.1 | Improved |
| more iterative steps raise correctly identified words (ablation) | CharNet · Total-Text training words | ratio of correct words: 64.95 -> 92.65 | Improved |
| add joint text recognition training (ablation) | CharNet R-50 · ICDAR 2015 detection | F-measure: 85.57 -> 89.70 | Improved |
| add joint text recognition training (ablation) | FOTS R-50 · ICDAR 2015 detection | F-measure: 85.31 -> 87.99 | Improved |
| add multi-scale inference | CharNet H-88 · ICDAR 2015 E2E (generic lexicon) | F-measure: 69.14 -> 71.08 | Improved |
| use Hourglass-88 backbone instead of ResNet-50 | CharNet · ICDAR 2015 detection | F-measure: 89.70 -> 90.97 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FOTS — FOTS: Fast Oriented Text Spotting With a Unified Network (CVPR 2018) · better on 1 of 1 shared result
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
- An End-to-End TextSpotter With Explicit Alignment and Attention (CVPR 2018 · similarity 0.91)
- Char-Net: A Character-Aware Neural Network for Distorted Scene Text Recognition (AAAI 2018 · similarity 0.89)
- Character Region Awareness for Text Detection (CVPR 2019 · similarity 0.89)
- Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features (ECCV 2022 · similarity 0.89)
- Towards End-To-End Text Spotting With Convolutional Recurrent Neural Networks (ICCV 2017 · similarity 0.88)
- A Text Detection System for Natural Scenes With Convolutional Feature Learning and Cascaded Classification (CVPR 2016 · 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.
