OCR, an acronym for Optical Character Recognition, is a process that converts a picture of text into actual, editable, text.
For example, you might find a picture of a meme on social media, which may be nothing more than text on a nice background saved in an image format, such as .jpg. Or you might scan a document you’ve received, which often results in a series of image files, or a PDF containing a series of images — “pictures”, if you will, of the individual pages.
Rather than retyping that text by hand to use elsewhere, you can use OCR to automatically extract the text for you.
As it turns out, Microsoft OneNote, present in Windows 10 and Microsoft Office, has basic OCR capability built in.
OCR starts with an image. That image — most commonly in “.jpg” or “.png” format — contains text you want to be able to use in some other context without having to re-type it all.
OCR is a computer analysis of that image. However, the analysis to identify individual characters can make mistakes. Even though OCR has improved as computers have become more powerful, it still introduces errors into its results.
There is a single, simple characteristic of text in an image that determines how accurate OCR will be: its clarity. The clearer the text, the more likely OCR will succeed. If the letters are small and fuzzy, OCR has a difficult time determining exactly what characters they are. This often results in visually similar characters being confused with one another — the letter “l” and the number “1” being a good example.
Clarity can mean that the text is large, or it can mean that smaller text is very crisp. In either case, or somewhere in between, the more clear the text is in the original image, the more accurate the OCR results will be.
OCR in OneNote
I’ll start with this image:
That’s a fairly typical example of an image that might be posted to social media as a “meme” in hopes of being shared a lot. It’s simply text on a background saved as an image — in this case, in”.jpg” format. Since it’s an image, you can only click on the whole image, perhaps to copy it, but you cannot click on and select only the text within it.
To extract the text from the image, we’ll start by opening the jpg file in a photo-viewing or image-editing application. Any will do, as long as it supports copying the image to the clipboard. There’s a good chance that simply double-clicking the image file in Windows File Explorer will open it in a suitable application. Since Paint 3D comes with Windows 10, I’ll open it in that.
Now, copy the image to the clipboard. In Paint 3D, I’ll type CTRL+A to select the entire image, and then CTRL+C to copy the image to the clipboard. Again, any application or technique you use to copy the image to the clipboard should be just fine.
Now, open OneNote, and create a new note or open an existing one. Click inside the note and type CTRL+V to paste the image from the clipboard into your OneNote note.
Now, right-click on the image and click on Copy Text from Picture.
Even though nothing will appear to have changed, this is where the magic happens. 🙂 OneNote has analyzed the image, identified the text displayed in the image, and placed a copy of that text into the clipboard.
Run your favorite text-processing program, such as Microsoft Word, WordPad, or, as I’ll use below, Notepad. Once the program is open on new document, type CTRL+V to paste the contents of the clipboard into your document.
You can see above that the text that was part of the picture has been placed into Notepad.
You’ll note there’s no formatting — no bold or italics, size changes, or anything else — just text. Depending on the original, line breaks may be preserved.
After reviewing the accuracy of the text as compared to the original, you can then do whatever you like with it, such as pasting it here and formatting it a little:
This article is the result of a Tip Of The Day suggestion made by reader David Phipps. It just seemed a little more than a “tip”. 🙂