Bartzi/see
Code for the AAAI 2018 publication "SEE: Towards Semi-Supervised End-to-End Scene Text Recognition"
This project helps computer vision researchers and machine learning engineers develop and train models for recognizing text in complex images. It takes images containing text, like house numbers or street signs, and outputs both the location of the text and the actual characters present. It is designed for those working with scene text recognition tasks, particularly using the SVHN dataset.
576 stars. No commits in the last 6 months.
Use this if you need to train a semi-supervised model to identify and transcribe text from images, especially in real-world scenarios with varied text placements.
Not ideal if you are looking for a pre-trained model for immediate use or if you lack experience with deep learning frameworks and GPU setup.
Stars
576
Forks
148
Language
Python
License
GPL-3.0
Category
Last pushed
Apr 26, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Bartzi/see"
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...