/ken-batcher-pp-ocr

Optical character recognition (OCR) project to catalog the work of PP-father - Kenneth E. Batcher

Primary LanguagePython

Kenneth E. Batcher - Documenting Historical Work with OCR

Dr. Kenneth E. Batcher is a highly accomplished Emeritus professor of Computer Science at Kent State University. He has received many prestigious awards like the IEEE Seymour Cray and ACM/IEEE Eckert-Mauchley Award. He discovered the Batcher Odd-Even Mergesort and Bitonic Sorter. And, he holds, or is affiliated with, 14 US Patents. His work in computer science and parallel processing earned him a place in history as a PP-father.

More information can be found about him here:

Unfortunately, during my time at Kent State University, Dr. Batcher passed away. As a tribute to him and in an effort to preserve his legacy/work, the computer science department opened a project to scan, document, and curate his work for archival, posting to a memorial website, and donation to a computer science museum in Irvine, CA.

To that end, this project was created.

My objective is to conduct an OCR-analysis on the scanned documents of Dr. Batcher's work. I intend to do some natural language processing on the results and create some interesting visualizations (like a word cloud) to potentially contribute to his memorial website. In any case, I feel that by doing this work I am learning about a esteemed man and his contribution to computer science.

Demo

Final Results

Getting Started

Windows:

  • Get Windows Subsystem for Linux (WSL) and pdf2image. You can follow this installation and usage guide.
  • Use pip to get the required imports.
  • Create the appropriate directories, 'images' and 'pdfs'.
  • Provide some pdfs in the pdf-directory.

Running the OCR-analysis

Once you have completed the 'Getting Started':

  • Run the 'go_OCR.py' script with a terminal command like 'python go_OCR'.

Built With

Authors

  • Matthew E. Miller - Initial work - Github

License

This project is licensed under the MIT License - see the LICENSE.md file for details

Acknowledgments

TODO: There is a group of KSU students from Fall '19 and Spring '20 which have created a memorial website for Dr. Batcher. I will try to find a link to their content.