This single session workshop builds on the previous course, From Image to Text: Working with OCR. The workshop will focus on developing a batch-processing workflow rather than processing documents individually.
The workshop will provide a practical example using a collection of scanned pages from a book (Sketches of Formosa by William Campbell). Participants will learn how to load images and apply OCR in batches. We will then perform a simple text analysis to demonstrate how the processed material can be used for research.
As part of the hands-on elements of the class, you are welcome to bring your own documents or images (scanned files, pdfs or images of text) to work with. Please note that we will use relatively “clean” material as method for tidying up images. Preparation of files will have been covered in the previous course earlier in the semester. If you were unable to attend the base course earlier in the semester, please review the repository resource to familiarise yourself.
By the end of the workshop, you will be able to outline the steps to implement image/text document processing packages using Python.
By the end of the workshop, participants will have a better understanding of how to work with a larger number of files using Python and how to turn them into searchable and analysable text data.
This is course requires pre-knowledge.
Basic familiarity with OCR tools package and Python based codebooks is helpful for following the workshop. Attendance at the course From Image to Text: Working with OCR is preferrable but not necessary.
- Understand how to inspect and organise collations of images and PDF files for batch processing.
- Use python to load and process multiple documents files automatically for OCR.
- Save OCR output as searchable text files.
By attending this course, you will become familiar with the following skills:
- Batch file processing for text analysis with Python
- Basic text cleaning and quality checking with Python
