图片文字识别
从图片/PDF扫描件批量提取中文、英文、数字、表格、代码和算式；支持裁剪、并行、断点续跑和低置信度标注
as observed 2026-10-18T21:45:32.509Z- Identifier
image-ocr- Source
- ClawHub
- Version observed
- 0.3.3
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-10-10T14:15:52.413Z
- Observations recorded
- 2
- Installs (reported upstream)
- 0
- Weekly downloads (upstream)
- 127
- Declared license
- MIT-0
Observation history
2026-10-18T21:45:32.509Z
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"Major update: Multi-language, multi-format, and advanced offline OCR with auto-preprocessing, multi-image/PDF support, and accuracy tuning.\n\n- Adds full offline support for Chin | "image-ocr 0.3.3: 8 boundary selftest, manual-review markers for handwriting/blur/lowres/stamp/vertical/merged tables, README/CHANGELOG dual-package docs" |
latestVersion |
"0.2.0" | "0.3.3" |
summary |
"从图片/PDF扫描件批量提取中文、英文、数字和算式文本，用于读取题目、截图和文档内容" | "从图片/PDF扫描件批量提取中文、英文、数字、表格、代码和算式；支持裁剪、并行、断点续跑和低置信度标注" |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.