Optical Character Recognition (OCR) is the electronic conversion of images of text into digitally encoded text using specialized software. OCR software enables a computer to convert a scanned document, a digital photo of text, or any another digital image of text into machine-readable, searchable, retrievable, and editable data. OCR data can then be used for a variety of applications, including data extraction, data/text mining, and text-to-speech technology. 

The OCR process typically involves at least three steps:

1. Scanning and/or opening a document in the OCR software,
2. Recognizing the text in the document using the OCR software, and 
3. Saving the new OCR-processed document in the file format of your choosing.

Depending on the quality of your document, you may also have to edit or "preprocess" the image to improve the quality and, thus, enable the OCR software to recognize the text more accurately. If you're working with text that the OCR software isn't equipped to recognize (handwritten or atypical typography), you might need to use language packages, patterns, and training data to supplement the software's default pattern recognition settings. And, finally, depending on the accuracy of the OCR, you may have to verify and correct ("post-process") the OCR-generated text. These steps could require a considerable amount of time and effort, depending on the quality and extent of your documents, so you will want to account for this in your process. 

For more on OCR, check out our Optical Character Recognition (OCR) @ Pitt guide, which provides information and resources for the following:

• Best Practices
• Out-of-the-Box OCR Tools
• Programmatic OCR Tools
• Example Projects