OCR-Style Character Recognition


Click image to enlarge

If your way of using Google Drive means that you upload PDFs or images containing text (such as document scans), Google Drive’s conversion tools might be just the thing for you.

Google Drive can scan your file to detect text in both PDFs and images, then make it into a standard, editable, Google Docs document format. The original image or PDF is embedded at the top of the document.

You can set this optional behaviour in the Drive interface upload settings, by clicking on the ‘cog wheel’ icon and then Upload Settings…. Remember to turn these options off again if you don’t want them permanently set.

For best results, the image or PDF files need to have sufficiently high resolution; Google recommends that each line of text should bef at least 10 pixels high. You’ll achieve superior results if your file uses common fonts like Courier, Arial or Times New Roman. Support for all non-Latin typefaces is still experimental, so you may not get the results you want.

You can select your document’s language from a drop-down menu.

Sharp, high definition, high contrast, well focussed and well lit images work best.

Image files (.jpg, .gif, .png) and PDF files (.pdf) are limited to 2MB. For PDF files, only the first 10 pages will be searched for text.

Files to be processed with OCR can take longer to upload into Google Drive than other formats, so be patient – PDFs may take a minute or two to process.

Leave a Reply

Your email address will not be published. Required fields are marked *