Scan paper lab results into a searchable PDF and run text recognition so clinicians can access and trend the values el…
Open the scanned PDF file in Adobe Acrobat.
Go to the Tools menu.
Select Scan & OCR from the tools list.
Click Recognize Text and choose In This File.
In the settings panel, ensure PDF Output Style is set to Searchable Image.
Click Recognize to start the OCR process.
Save the PDF after OCR is complete.
Best practiceFor best OCR accuracy, scan your documents at 300 dpi and ensure the images are clear before running OCR.
After OCR completes, you can search, copy, and highlight text in your previously scanned PDF.
This runs in the Acrobat app - there is no separate API for this task.
Acrobat's OCR feature is designed to work only on pages that are images. If a page already has real, selectable text, Acrobat will not try to recognize text on it again. This message means your page already has text, so OCR is not needed. You can still search the document if it already has text.
For the best OCR accuracy, you should scan your documents at 300 dpi (dots per inch). This resolution provides enough detail for the software to recognize characters correctly. Scanning at lower resolutions, like 72 dpi, can make the text recognition less accurate.
Yes, you can automate this. The Adobe PDF Services API offers an 'OCR PDF' operation. This API lets you programmatically convert image text in your PDFs into a searchable layer. It's useful for large-scale archiving or indexing tasks.
Before you start the text recognition process, it's very important to choose the correct language for your scanned lab results. In the 'Scan & OCR' tool, you will find an option to set the language. Selecting the right language helps Acrobat's OCR engine accurately identify and convert the text into a searchable layer.