mindocr and mmocr
These are competitors offering overlapping end-to-end OCR pipelines (text detection, recognition, and understanding), both built on different deep learning frameworks (PyTorch/MMengine vs. MindSpore) but targeting the same use cases, though MMOCR has significantly broader adoption.
About mindocr
mindspore-lab/mindocr
A toolbox of ocr models and algorithms based on MindSpore
This tool helps businesses and researchers automatically extract text from images and documents. You input images containing text, and it outputs the detected text and its location, making it easier to digitize information. It's designed for anyone needing to process visual data to get at the embedded text, such as for data entry, archival, or content analysis.
About mmocr
open-mmlab/mmocr
OpenMMLab Text Detection, Recognition and Understanding Toolbox
This project helps convert images containing text, like scanned documents or photos, into machine-readable text. It takes an image as input and outputs the detected text and its location, enabling tasks like searching document content or automating data entry. It's designed for developers and researchers building applications that need to extract information from visual content.
Scores updated daily from GitHub, PyPI, and npm data. How scores work