OCR in Python Tutorials
Python Tutorials for Digital Humanities |
10 videos |
Updated 3 years ago
This playlist is one component of a work-in-progress textbook on OCR in Python. As I complete this series, I will add to the textbook which will consist of Jupyter Notebooks compiled as a JupyterBook. The repo can be found here: github.com/wjbmattingly/ocr_python_textbook.
In all, the watcher of this playlist will learn the fundamentals of performing quality OCR in Python. I expect no prior knowledge of the three essential libraries: Pillow, OpenCV, and PyTesseract.
The goal of this series is to introduce you to the basic concepts of OCR, the essential functions and classes of the requisite libraries, and the ability to leverage Tesseract models to have quality raw text. I will also provide some preliminary steps to clean the output.
