pix2tex: Using a ViT to convert images of equations into LaTeX code.
Repository Index
47,133 repositories indexed
1–8 of 8 · Most stars
OCR model that handles complex tables, forms, handwriting with full layout.
OCR & Document Extraction using vision models
An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.
Translated[Captcha Recognition - Training] This project is based on CNN/ResNet/DenseNet+GRU/LSTM+CTC/CrossEntropy to realize verification code identification. This project is only for training the model.
- captcha-recognition
- tensorflow-tutorials
- ocr
- tensorflow
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy
Scan the MRZ code of a passport and extract the firstname, lastname, passport number, nationality, date of birth, expiration date and personal numer.
- mrz
- passport
- scanner
- ocr
On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese, English, Japanese and Korean.