Research map / Detection and segmentation / CNN features
Start, Follow, Read: End-to-End Full-Page Handwriting Recognition
Curtis Wigington, Chris Tensmeyer, Brian Davis, William Barrett, Brian Price, Scott Cohen
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 |
|---|---|---|---|
| provide ROI annotations at test time (mask out other regions) | Start, Follow, Read · ICDAR2017 HWR | BLEU: 72.3 -> 73.0 | Improved |
| provide ROI annotations at test time | BYU (competition winner) · ICDAR2017 HWR | BLEU: 57.3 -> 71.5 | Improved |
| use SFR page-level model instead of BYU winner, without ROIs | ICDAR2017 HWR · ICDAR2017 HWR (without ROIs) | BLEU: 57.3 -> 72.3 | Improved |
| use SFR instead of Bluche page-level model | IAM line-level · IAM | WER: 24.6 -> 23.2 | Improved |
| use SFR instead of Bluche page-level model | RIMES line-level · RIMES | WER: 12.6 -> 9.3 | Improved |
| use SFR instead of Puigcerver (which uses segmentation annotations) | RIMES line-level · RIMES | CER: 2.3 -> 2.1 | Improved |
| add end-to-end backpropagation through HWR, LF and SOL networks (ablation) | Start, Follow, Read · ICDAR2017 HWR | recognition performance | No clear effect |
Later papers that compared with this method
1 later accepted paper reports Start-Follow-Read as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- PageNet: Towards End-to-End Weakly Supervised Page-Level Handwritten Chinese Text Recognition (IJCV 2022 · 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
- OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold (CVPR 2020 · similarity 0.87)
- Handwritten Text Recognition: A Survey (TPAMI 2025 · similarity 0.87)
- Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognition (NeurIPS 2016 · similarity 0.86)
- General Detection-based Text Line Recognition (NeurIPS 2024 · similarity 0.86)
- Reading between the Lines: Image-Based Order Detection in OCR for Chinese Historical Documents (AAAI 2024 · similarity 0.84)
- MetaWriter: Personalized Handwritten Text Recognition Using Meta-Learned Prompt Tuning (CVPR 2025 · similarity 0.84)
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.
