OCR explained: how Drive finds text inside your scanned PDFs
Optical character recognition sounds intimidating but it's actually one of the most useful, most invisible features in modern cloud storage. Here's how it works and why it matters.
If you've ever scanned a receipt and then spent 20 minutes scrolling through folders trying to find it six months later, OCR is the feature you didn't know you needed.
What OCR does
OCR — Optical Character Recognition — looks at an image of text (a photo of a letter, a scanned receipt, a screenshot) and converts it into real, searchable text. Modern OCR is accurate enough to read handwritten grocery lists and 40-year-old typewriter pages.
How Drive uses it
When you upload an image or a scanned PDF, Drive runs it through a client-side OCR pass and stores the extracted text alongside the file. Next time you search for "Costco" or "prescription refill", Drive finds the receipt — not because you named it well, but because Drive read what was inside.
What it doesn't do
Drive's OCR runs on your own device in your browser. We don't send your receipts to a third-party OCR API. The extracted text never leaves your account and is never used to train any machine-learning model. It just makes search work like magic.
The receipt for that air fryer you bought in 2023 is one search away. Try it: snap a photo of something on your desk right now, upload it, then search for a word on the paper. You'll see what we mean.