What is Optical Character Recognition (OCR) in Google Drive?

Optical Character Recognition (OCR) uses automated computer algorithms to convert images that include text into text documents. These images can be converted individually or in multi-page PDF documents. Some types of files that are compatible with OCR are image or PDF files obtained from flatbed scanners or photos taken with digital cameras or mobile phones.

File size limitations

  • The maximum file size for images including .jpg, .gif, .pgn, and .pdf is 2 MB.

Requirements of .pdf files for the best results

  • Minimum height of 10 pixels for text in the document, high-resolution files are best
  • The document must be right-side up, Google Drive will not recognize files with a different physical orientation
  • The image quality should be sharp,with even lighting, and clear contrasts. Motion blurred or bad camera focus will result in decreased quality of the detected text
  • The language, fonts, and character sets for the Google OCR engine recognizes a very large assortment of character sets automatically. The OCR engine can read left to right, right to left, and text written vertically. Better results are common with Ariel and Times New Roman fonts.