Torbjorn Zetterlund

Sat 14 2015

The hidden OCR feature of Google Drive

by bernt & torsten

Google Drive’s Optical Character Recognition (OCR) lets you convert images with text into text documents using automated computer algorithms. Images can be processed individually (.jpg, .png, and .gif files) or in multi-page PDF documents (.pdf).

These are some of the types of files suitable for OCR:

  • Image or PDF files obtained using flatbed scanners
  • Photos were taken with digital cameras or mobile phones

How do you go about getting your paper documents converted to a Google Docs document, the first step is finding the images or PDFs that you want to use with OCR to convert to text files. Google Drive currently supports OCR for .jpeg, .gif, .png, and PDF files up to 2MB in size.

Tip: If you want to convert multiple pages to text, PDF format is the most efficient as all pages can be uploaded in one batch. However, the text will only be extracted from the first 10 pages of the PDF.

Getting ready to Upload

There are a few rules of thumb to produce optimal results from OCR in Google Drive. Make sure your file is high resolution with clear contrasts and even lighting.  Additionally, make sure that the text being scanned is horizontal and read from left to right. Standard typefaces, such as Helvetica and Times New Roman, will produce better results than more obscure typefaces. If you have a document that’s rather unreadable, you can still attempt to OCR it, but the results likely won’t be that nice.

While Google Drive supports OCR for many different languages, OCR on languages that use non-Latin character sets is still buggy and may not produce desirable results.

Uploading to Google Drive

If the files are on your computer, make sure that their file format is one of those supported by Google Drive. If the document or photo you want to use is physical, scan them onto the computer,  if you own a scanner. If you don’t have a scanner, your phone can be used in place of one. If you own an Android phone, you can install the Google Drive app on your phone.

Google Drive - Android Apps on Google Play

With the Drive app for Android, you can scan important documents, like receipts, letters, and billing statements, as long as you have a camera on the back of your device. After you’ve scanned a document, the app will save it as a searchable PDF file and store it right in your Drive.

Go to the Google page here to get details on how to use Google Drive for Android with OCR

To add your documents to Google Drive to get them OCRed, go into your Google Drive account. On the My Drive page, click the Settings button on the right side of the page. Under Upload Settings, check off the Convert text from uploaded PDF and image files and the Confirm settings before each upload option.

Google Drive OCR
Google Drive OCR

Make sure the proper settings are enabled before proceeding to upload the document. If you using the New Google Drive goes back to the old to find the settings.

Then, click the Upload button next to Create button on the left side of the page. Select Files, and find the file that you want to convert to text in Finder. Click Open.

Upload File Google Drive
Upload File Google Drive

An Upload Settings panel will appear. Select the proper language from the Document Language drop-down menu, and leave the Confirm settings before each upload box checked.

Screen Shot 2015-02-13 at 14.45.43
Select the proper Document language from the drop-down and keep Confirm settings checked off.

Click Start upload once you have confirmed your settings. Upload progress can be monitored in the bottom right corner of the page. Uploads typically last around 30 seconds for image files and up to a minute for multi-page PDFs.

Once the upload is complete, a new Google Doc appears in the drive, titled the same as the name of the original file. Open the new document, and rename it if need be. The original file is displayed on the top of the document, and the text extracted from the document is displayed directly below.

Scan google doc document

Google’s OCR technology does its best to retain the original formatting of the scanned document; however, some of it may be lost in the translation process. Luckily, changes can easily be made due to the fact that the text is editable.

One huge advantage of using OCR in Google Drive is that you can easily share the new document with whoever. To do so, go to File > Share, and you can add collaborators by sharing a link or sending an invitation via email or you can export the document as an editable text document, such as a Word Document or a Plain Text document, by going to File > Download As and selecting the format you want.