How to Translate a Scanned PDF and Keep the Page Layout

A scanned PDF has nothing to translate. The page is a picture of a document; the words in it are ink, not text. Whatever translates it has to read the page, lift the printed words off the image without disturbing what was printed around them, and set the translation in their place.

Getting the words off is the part that decides whether your document survives. It is worth two minutes to understand, because it also tells you what to expect from the result.

Lifting the words off without taking the page with them

To a computer, the line of a table, the ring of a registry seal and the stroke of a signature are the same thing as the letters: dark pixels on light paper. Erase too eagerly and the table loses its grid. Erase too carefully and the tails of the old words stay behind, sitting beside the new ones.

There is one property that separates them, and it does not depend on recognising anything: a ruled line is a long straight run of ink, and no stroke inside a letter is. Lines can be found by that shape alone and left where they are, while everything else in the area comes away, including the parts of letters that touch a line.

That last clause is what makes it work on real paper. An underline in a scan usually touches the feet of the letters above it, so the whole thing is one joined-up shape; treat it as a shape and sparing the line spares the sentence with it. Treat it as runs and the line is a run while the letters are not, so the letters come away and the underline stays.

Ink that carries on past the area is left alone for a different reason: a seal ring or a signature is not part of this line's text. Seals, signatures, logos and photos keep the original's pixels, and the words printed around them are replaced.

In practice that means the grid of your table, the stamp on your certificate and the signature at the bottom arrive intact, and the words they surround arrive in your language.

What came out on a real document

We translated a two-page Brazilian higher-education transcript from Portuguese into English, both pages in a single run. It is a sample that carries every element Portaria MEC nº 1.095 requires a transcript to state, scanned at 400 DPI in colour.

The pages are demanding ones: a course table that runs across both pages, blocks of label-and-value pairs, a grading legend with numbers inside the sentences, a registry seal between the signature rules, and a long authenticity code.

Page 1 is on top and page 2 below, the Portuguese scan on the left of each pair and the English on the right.

Here is what came back.

• The table. All 44 course rows, 27 on page 1 and 17 on page 2, kept their order and their ten columns. Hours, credits, grades and attendance match the original cell by cell.
• Codes. The authenticity code 9F3C-27B1-AD40-5E88, the web address and every course code came through character for character, and the code and address can be copied out of the text layer.
• Totals. 3035, 2835, 200, 240, 173 and 7,63 are unchanged.
• The legend. It is translated with its numbers intact, and the result codes in the table follow it: AP is now P for Pass.
• Seal, crest and stamps. They kept the scan's pixels, compared at 300 DPI.
• Dates. They stayed in the Brazilian day/month/year form: 09/05/2023 still reads 09/05/2023, which is 9 May. A reader who expects the month first needs to know that, and you can rewrite any date on the page.

Portuguese above, English below. The numbers inside the legend's sentences are the same, and the registry seal and the signature lines are the scan's own.

And if a line is not the way you need it

Any translation of an official document has a few lines only you can settle: a course title your registrar words differently, a job title with a particular equivalent in the country you are applying to, a name transliterated the way the rest of your paperwork spells it.

So the rebuilt page is not a picture with a translation painted on. It carries real, selectable text. You can search it, and you can copy an identifier out of it and paste it into a form.

You can also change it. Selecting any line shows what it says in both languages, and every line the translation set, from the table headers to the footer, can be rewritten in the online editor. Type the change and the page is laid out again from the original scan, with your wording in place of the old one.

A course title on page 2 opened in the editor. The Portuguese it came from is above the English you can change, and saving sets the page again with your words.

Four things worth a look before you send it

These four are quick, and they are the ones your own eyes are best at.

Follow one row all the way across. On any table, pick a couple of rows and read them left to right. The grade, the hours and the status should still read together as one record.

Copy an identifier and paste it somewhere. Registration numbers, reference codes and validity strings exist to be typed into other systems. Paste one and see it arrive whole.

Read the small print. Legends and footers carry the rules the rest of the page depends on: the grading scale, the attendance minimum, the validity code. Check the numbers inside those sentences.

Read the two or three lines a decision will turn on. Wording is where your judgment is worth more than any automatic check.

Before delivery, a second AI model from a different provider reviews each page against the scan image itself, so a figure the translator misread can be caught there and not only by you. A place that only the original can settle is marked on the translated page for you to confirm.

On the transcript, the file marked page 1, the page with the longer table, as not fully reviewed: the second model's review of it stopped before the end. That page is the one to read against the scan first. Two translator's notes name the sample stamp and the registry seal.

Every LangTo account starts with 5 free pages, enough to translate a short scan and check the rebuild before you buy more. A PDF can have up to 20 pages and 50 MB, and every page of it is translated. Translate a scanned PDF