JinpengLI/deep_ocr
A Chinese character OCR system built on deep convolutional neural networks (Caffe) that outperforms tesseract for Chinese text recognition.
Not currently ranked — collecting fresh signals.
star history
The project provides a deep learning-based alternative to tesseract specifically for Chinese character recognition. It uses convolutional neural networks trained on Caffe to recognize individual Chinese characters from images. The system includes scripts for batch recognition and supports training custom character models based on published deep learning research for handwritten Chinese character recognition.
Frequently asked
- What is JinpengLI/deep_ocr?
- A Chinese character OCR system built on deep convolutional neural networks (Caffe) that outperforms tesseract for Chinese text recognition.
- Is deep_ocr open source?
- Yes — JinpengLI/deep_ocr is an open-source project tracked on heatdrop.
- What language is deep_ocr written in?
- JinpengLI/deep_ocr is primarily written in Python.
- How popular is deep_ocr?
- JinpengLI/deep_ocr has 1.5k stars on GitHub.
- Where can I find deep_ocr?
- JinpengLI/deep_ocr is on GitHub at https://github.com/JinpengLI/deep_ocr.