Summarizing my self-learned tutorials in the topic of building OCR python applications.
This repo includes the following tutorials:
- ocr-with-tesseract is the tutorial from nanonets blog
- ocr_docker is an example of building a simple OCR web app with docker. Source
The other tutorials are from pyimagesearch:
- ocr-for-non-english
- basic-tesseract-ocr
- detecting-and-ocring-digits
- opencv-sudoku-solver-and-ocr
- four-points get-perspective transform example
- building a document scanner opencv
- image alignment and registration opencv
- using-ml-to-denoise-images-for-better-ocr-accuracy
Updating ...
Current installed packages:
- Python 3.9.7
- OpenCV cv2.version '4.5.3'
- tesseract v5.0.0-alpha.20210811 leptonica-1.78.0