doctr
OCR engine
A deep learning-based OCR library that enables efficient text parsing and recognition from documents
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.
4k stars
43 watching
444 forks
Language: Python
last commit: 10 days ago
Linked from 1 awesome list
deep-learningdocument-recognitionocroptical-character-recognitionpytorchtensorflow2text-detectiontext-detection-recognitiontext-recognition
kba/awesome-ocrRelated projects:
| Repository | Description | Stars |
|---|---|---|
 deepdoctection/deepdoctection | An integrated framework for document AI tasks using deep learning models. | 2,588 |
 ocrmypdf/ocrmypdf | A tool that adds OCR text to scanned PDF files, allowing them to be searchable and copy-pasted. | 14,140 |
 tesseract-ocr/tesseract | An OCR engine capable of recognizing text in images from various languages and formats. | 62,363 |
 docarray/docarray | A Python library for representing, transmitting, storing, and retrieving multimodal data | 2,983 |
 emedvedev/attention-ocr | A TensorFlow model for recognizing text in images using visual attention and a sequence-to-sequence architecture. | 1,077 |
 ocropus-archive/dup-ocropy | A collection of tools for document analysis and OCR. | 3,422 |
 clovaai/deep-text-recognition-benchmark | Provides a benchmarking framework and implementation for deep learning-based text recognition models | 3,755 |
 hrnet/hrnet-semantic-segmentation | An implementation of a high-resolution neural network architecture for semantic segmentation tasks. | 3,156 |
 brightmart/text_classification | An NLP project offering various text classification models and techniques for deep learning exploration | 7,861 |
 doccano/doccano | An annotation tool for machine learning practitioners to create labeled datasets | 9,572 |
 ibm/max-ocr | An optical character recognition system deployed as a web service using a trained Tesseract OCR model | 47 |
 x-plug/mplug-docowl | A large language model designed to understand documents without OCR, focusing on document structure and content analysis. | 1,563 |
 huggingface/transformers | A collection of pre-trained machine learning models for various natural language and computer vision tasks, enabling developers to fine-tune and deploy these models on their own projects. | 135,022 |
 vikparuchuri/marker | Converts PDF to markdown quickly and accurately using a pipeline of deep learning models | 17,804 |
 mittagessen/kraken | An OCR system optimized for historical and non-Latin scripts | 748 |