Find image files faster with OCR

Dropbox makes it fast and easy to find your images and scanned docs by simply searching for text that’s in them.
Library of OCR scanned pdfs stored in Dropbox

Be more organized with OCR online

If you have a ton of scanned PDF and other image files saved in cloud storage, how do you find what you’re looking for in a pinch? With Optical Character Recognition (OCR), it’s fast and easy. OCR extracts actual text from scanned images so all you need to do is search for your image using a term or keyword. 

Scanner app capturing an image of a receipt

Turn scanned images into text-searchable PDFs

Dropbox eliminates the time-consuming task of processing large documents manually. Scan and store receipts, bills, photos, legal contracts, infographics from work, or even your next flight itinerary. When you’re ready to access these files from Dropbox, just input a text keyword in the search bar. A short list of words or thumbnail images will pop up so you can find your docs fast.

Scanner app capturing an image of a signed contract

Explore how OCR can help your business

Just about any business can benefit from OCR technology for greater productivity. A lawyer, for example, can search for any case file simply by searching for a particular word. Banks, medical offices, and advertising and marketing firms can all use OCR to streamline their businesses and virtually eliminate the need to file and store physical paper docs.

Scanner app with a round and blue scan button in the bottom right corner

Frequently asked questions

OCR stands for Optical Character Recognition or Optical Character Reader. OCR is a technology used to “recognize” or “read” text featured in image files. OCR either converts images of typed, handwritten, or printed text from the files—including scanned documents, photos of a document, photos with signs or scenes with type, or subtitles on an image—into text that machines can process and search through. Currently, Dropbox uses OCR to recognize the text of your PDFs to make them searchable by their contents.

Yes, OCR is based on machine learning. OCR technology replicates the human ability to recognize various text patterns, fonts, or styles on images, documents, and more. This technology is possible because of the capability of machines to learn. OCR is a prime example of the type of large scale projects involving computer vision and machine learning that engineers at Dropbox are working on all the time. 

Even though they sound similar, there are major differences between OCR and ICR. OCR translates scanned images of text and turns these scans into machine-encoded text. ICR is a type of OCR but it’s more specific to text. An ICR can learn different fonts and styles of handwriting rather than just translating text from a scanned image. 

OCR uses pattern or feature recognition to define each individual character in different ways, then “reads” the text and converts it into an indexed file that can be searched.

See more features

Collaborate with team members easily

Content collaboration

Easily collaborate, edit, and share content with team members

Secure file backups

File backup

Backup your files and protect against data loss simply and securely

Backup photos automatically

Photo backup

Automatically backup your photos to the cloud from any device

Scanning app for documents

Doc scanner app

Take the work out of paperwork with the doc scanner app