awesome-scene-text
github.com/janzd/awesome-scene-text ↗A curated list of papers and resources for scene text detection and recognition
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me open source ocr systems resources from awesome-scene-text"
Installation instructions →What's inside
Tools & Libraries
- codeOpen Source OCR Systems
Comprehensive OCR toolbox with 7 detection and 5 recognition algorithms [
- codeOpen Source OCR Systems
Ready-to-use OCR with 80+ languages support (PyTorch-based) [
- codeOpen Source OCR Systems
Unified benchmark system for training and evaluating scene text models [
- codeOpen Source OCR Systems
Powerful, lightweight OCR toolkit supporting 100+ languages [
- OCR comparison: Tesseract vs EasyOCR vs PaddleOCR vs MMOCRComparison
- Open-Source OCR Libraries: A Comprehensive StudyComparison
Datasets & Benchmarks
- downloadMajor Datasets
20,000 images, Chinese street view trademark dataset [
- downloadMajor Datasets
462 images (229 train, 233 test), 1,944 text instances [
- downloadMajor Datasets
509 images (258 train, 251 test), 2,266 text instances, English only [
- downloadMajor Datasets
1,000 street view images, 2,955 text instances [
- downloadMajor Datasets
450,000 images (430,000 train, 20,000 test), horizontal/multi-oriented/curved text [
- downloadMajor Datasets
1,500 images (1,000 train, 500 test), 17,548 text instances, first incidental scene text dataset [
Scene Text Recognition
Text Generation with Diffusion Models
Weakly Supervised Methods
End-to-End Text Spotting
Showing a sample of 333 resources. View the full list on GitHub →