jideilori/ocr-ml
A custom OCR built with HOG and logistic regression
Need to automatically read specific text from images, like license plates or product codes, where standard OCR struggles? This tool helps you create a specialized system to recognize characters or numbers that look a certain way in your particular images. You provide example images with the text highlighted, and it learns to extract that information for you, outputting the recognized text.
No commits in the last 6 months.
Use this if you have a very specific type of text (e.g., car license plates, part numbers on labels) that appears consistently in your images and off-the-shelf OCR isn't accurate enough.
Not ideal if you need to read general document text, handwriting, or highly variable fonts and layouts, as it requires tailored training for specific patterns.
Stars
9
Forks
3
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Jun 04, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jideilori/ocr-ml"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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...