Deskew and straighten a scanned PDF
VellumPDF works out each page’s reading direction and tilt, and proposes the fix.
Your files never leave your deviceDrop your scanned PDF here
or click to browse your files
How to straighten a scanned PDF, step by step
VellumPDF first looks for the right reading direction from the text lines, and only calls on character recognition when that is not enough.
Drop in the scanned PDF
Analysis starts right away, page by page, with a cancellable progress bar.
Let VellumPDF measure the text structure
If the lines give a clear signal, the rotation axis (0°/180° versus 90°/270°) is decided without OCR.
Let OCR settle the direction if needed
If ambiguity remains (0° or 180°, 90° or 270°), the built-in text recognition reads a middle strip of the page both ways and keeps the more confident verdict.
Go through the grid of thumbnails
Every page shows the angle chosen and the method used: text lines, OCR, or “No text found”.
Correct a page by hand if needed
Clicking a thumbnail rotates it a further quarter turn, independently of the automatic verdict.
Click “Straighten N page(s)”
Then download the corrected document.
A page with no text — a photo, an illustration, a blank page — offers nothing to measure and stays unchanged: you can always rotate it by hand. The rotation applied is just a display instruction stored in the PDF, never a rasterization.
Frequently asked questions
How does VellumPDF work out which way up a scanned page is?
In two steps. It first measures how ink is spread across the page: horizontal text alternates inked lines with empty gaps, which separates upright pages from pages lying on their side without reading anything. To then tell an upright page from an upside-down one, text recognition reads a strip in the middle of the page both ways and keeps the direction it is most confident about — the only method that proved reliable in testing. When recognition is not available, VellumPDF corrects the axis only and leaves the page as it is rather than guess.
Does rotating degrade the quality of the scan?
No. The rotation is written into the PDF as a display instruction: page content is not turned pixel by pixel, rasterised or recompressed. The original sharpness is preserved, text stays selectable, and the change can be undone by applying the opposite rotation.
Why are some pages left unchanged?
Because they offer nothing to measure. A full-page photo, an illustration, a flat colour area or a blank sheet has no text lines: VellumPDF says so on the thumbnail and leaves the page alone rather than guessing. You can still turn it yourself by clicking on it.
Does the text recognition download anything?
No. The recognition engine and its language model are served from your own device, as they are for VellumPDF’s OCR tool, and they are loaded only if a page genuinely needs them. On a document whose text lines settle the question — the usual case — recognition never starts.
Does VellumPDF also fix a slightly tilted scan?
Yes. Once the reading direction is known, VellumPDF measures the slope of the text lines to a twentieth of a degree, up to 15° either way. The page is then straightened by rotating its content inside the PDF itself: nothing is turned into an image and the text stays selectable. Scan corners that stick out of the page are trimmed; a checkbox turns this correction off.