clovaai/deep-text-recognition-benchmark
Text recognition (optical character recognition) with deep learning methods, ICCV 2019
This project helps you accurately convert images of real-world text, like signs or labels, into digital text that computers can understand. You feed it an image containing text, and it outputs the extracted text. This tool is ideal for researchers, data scientists, or anyone working with optical character recognition (OCR) systems, particularly those focused on challenging 'scene text' found in photos, rather than scanned documents.
3,926 stars. No commits in the last 6 months.
Use this if you need to build, compare, or evaluate advanced text recognition models for extracting text from diverse and complex real-world images.
Not ideal if you primarily need to digitize text from clean, scanned documents or require a simple, off-the-shelf OCR application without deep learning model comparison capabilities.
Stars
3,926
Forks
1,131
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Mar 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/clovaai/deep-text-recognition-benchmark"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
JaidedAI/EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin,...
breezedeus/CnSTD
CnSTD: 基于 PyTorch/MXNet 的 中文/英文 场景文字检测（Scene Text Detection）、数学公式检测（Mathematical Formula...
githubharald/SimpleHTR
Handwritten Text Recognition (HTR) system implemented with TensorFlow.
felixdittrich92/OnnxTR
OnnxTR a docTR (Document Text Recognition) library Onnx pipeline wrapper - for seamless,...
mindee/doctr
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for...