chineseocr/darknet-ocr
Chinese OCR system based on darknet using CTPN for text detection and CNN+CTC for character recognition.
Not currently ranked — collecting fresh signals.
star history
This project implements a complete OCR pipeline using the darknet framework. It uses CTPN (Connectionist Text Proposal Network) for natural scene text detection and a CNN combined with CTC (Connectionist Temporal Classification) loss for text recognition. The system supports both GPU and CPU execution, provides a web service for image and URL-based text extraction, and includes training datasets and model files for Chinese text recognition.
Frequently asked
- What is chineseocr/darknet-ocr?
- Chinese OCR system based on darknet using CTPN for text detection and CNN+CTC for character recognition.
- Is darknet-ocr open source?
- Yes — chineseocr/darknet-ocr is open source, released under the MIT license.
- What language is darknet-ocr written in?
- chineseocr/darknet-ocr is primarily written in C.
- How popular is darknet-ocr?
- chineseocr/darknet-ocr has 1.2k stars on GitHub.
- Where can I find darknet-ocr?
- chineseocr/darknet-ocr is on GitHub at https://github.com/chineseocr/darknet-ocr.