isee15/Card-Ocr
Chinese ID card OCR system using Tesseract and Keras to extract text fields from identity document images.
Not currently ranked — collecting fresh signals.
star history
This project implements optical character recognition specifically for Chinese national ID cards. It uses Tesseract OCR with custom training data for digit and text recognition, along with OpenCV image preprocessing including grayscale conversion, inversion, dilation, and contour detection to locate and isolate ID number regions. The system extracts fields such as name, gender, ethnicity, birth date, address, and ID number from card images, with PaddleOCR integrated as an alternative engine for improved Chinese character recognition.
Frequently asked
- What is isee15/Card-Ocr?
- Chinese ID card OCR system using Tesseract and Keras to extract text fields from identity document images.
- Is Card-Ocr open source?
- Yes — isee15/Card-Ocr is an open-source project tracked on heatdrop.
- What language is Card-Ocr written in?
- isee15/Card-Ocr is primarily written in Jupyter Notebook.
- How popular is Card-Ocr?
- isee15/Card-Ocr has 496 stars on GitHub.
- Where can I find Card-Ocr?
- isee15/Card-Ocr is on GitHub at https://github.com/isee15/Card-Ocr.