Optical Character Recognition: Explained

Today’s post is from Museum Explainer Meredith Rector.

Sometimes even computers need help.

This is something that I have learned in the past few weeks volunteering at the Rakow Research Library. I work as a Museum Explainer, but when I had a volunteer requirement to fulfill, I wanted to delve into the Library since it was an area of the Museum I had yet to explore. This way I can assist Museum guests in more ways and learn more interesting things about glass.

At the Rakow Library, I work with OCR or Optical Character Recognition. This process uses a program that reads articles, books and other publications in the Library’s collection and identifies text and images. After the computer reads through a document, I go back through to be sure that the program has recognized all of the text and images as such, respectively—this process is called formatting. Once the formatting is completed, the program goes back and reads through the text in the document and thus begins a process called verification. Similar to spell check in a Word document, verification involves looking at a selected piece of text and correcting the computer if it has read a part of the text (or all of it) incorrectly. Once this process is finished in one document, there are always plenty more to be read.

OCR Screenshot

Similar to spell check, verification involves looking at a selected piece of text and correcting the computer if it has read the text incorrectly.

The purpose of OCR is ease of use and accessibility. When images and characters are recognizable, they can be copy and pasted from one place to another and they become searchable in the Library’s database. This way if a guest is looking for a certain piece from a trade catalog, a librarian can more easily track down information for them.

While at times this process can be tedious (because reading fractions can be very tough for a computer), I’ve really enjoyed it. Recently I’ve been looking through trade catalogs and I find it very interesting to see the various pieces that companies made and sold. Below are just a couple of my favorite examples.

This slideshow requires JavaScript.

Search and browse full-text PDFs of trade catalogs and other Rakow Library materials.

The Rakow Research Library is open to the public 9am to 5pm every day. We encourage everyone to explore our collections in person or online. If you have questions or need help with your research, please use our Ask a Glass Question service.

Leave a Reply

%d bloggers like this: