Tech Tips on Computers, Internet, Blogging, Web Development, Social Media, Android and more

Full width home advertisement

Post Page Advertisement [Top]

Optical Character Recognition, or OCR, is a technology that enables you to convert different types of documents, such as scanned paper documents, PDF files or images captured by a digital camera into editable and searchable data.

Google Drive now has a feature that lets you convert scanned images and PDFs to text. It is a painless process that will save you a lot of typing if in case you need to get the text from scanned documents. All you need is a Google Account and of course the image (that contains the text) to upload.

In a nutshell, the process to convert the image (containing text) to text is:


    • Upload the Image to Google Drive
    • Open the Image in Google Drive with "Google Docs"
    That's it. The extracted text is displayed right below the image in Google Docs.

    Before you jump with excitement, here are a few thing to take care of:
    Scanning the documents:
    • Google Drive will be able to read whether the image is from a flat-bed scanner, from a digital camera or from a smartphone, provided the resolution of the file is not too bad, there is good contract etc.
    • If you are clicking images from digital camera or smartphones, make sure that there is good light source. Darker images will be harder to recognize by the OCR.
    • If your image needs some retouching, edit the image either on the phone or computer to improve contract etc.
    Once you have the image ready, you are ready to upload to Google Drive.
    •  Go to https://drive.google.com
    • Upload the image to Google Drive by simply drag and dropping.
    • Right-Click on the image and select "Open With", then select "Google Docs"

    • The image will open in another tab
    • Once processed, you should see the image as well as the extracted text below.

    • Edit texts if required.
    • If you need only the text, you can remove the image. 
    • Download the file as Microsoft Word document (.docx).
    I tested with several images and the accuracy is very good if the resolution and clarity is good. For images with less contract, the accuracy will be lower. So, prepare the images well before converting.

    File size limitations
    • The maximum size for images (.jpg, .gif, .png) and PDF files (.pdf) is 2 MB. 
    • For PDF files, only first 10 pages  is searched when searching for text to extract.

    2 comments:

    1. I find another free online ocr to convert image to text, it's using google tesseract ocr 3.02.

      ReplyDelete

    Bottom Ad [Post Page]