How to Extract Text from a PDF Using OCR on iPad
Download Highlights for free. Not on an iPad? Checkout the Mac and iPhone guides.
If a region of your PDF is not searchable (does not contain a text layer), Highlights can extract the text using machine learning.
1. Make an image selection over the text you want extracted:
![Image selection over text of interest in the PDF](/img/pdf/ocr-selection.png)
2. Tap on the image selection to bring up the annotation popover:
![](/img/ipad/popover/image-selection-compact.png)
3. Tap the Text Recognition button:
![](/img/ipad/popover/text-recognition-selection.png)
Wait for the text to be recognized:
![](/img/ipad/popover/text-recognition.png)
Once the recognition is complete your text will appear in the comment:
![](/img/ipad/popover/text-recognized.png)
And the image in your notes will be converted to text:
![](/img/note/ocr-text.png)
4. Tap the Smart Copy button to copy the extracted text
![](/img/ipad/popover/text-recognized-copy.png)
The default language for text recognition is English (US), but you can change the text recognition language in settings:
![](/img/ipad/settings/recognized-language.png)