Guide

Convert a scanned legal document to Word without retyping it.

A scanned lease, deed or contract is a picture of a page. It cannot be searched or edited until someone turns the picture back into words and structure. Firms have paid people to retype them, or used basic converters that left the page hard to edit.

Last updated

What is in a scan

A scan holds the picture, not the structure.

Optical character recognition (OCR) can read printed and typewritten text from a scan. It cannot see that a line is a heading, that a paragraph is clause 1.1, or that a note at the foot of the page belongs with the body text. Those things have to be rebuilt before the document is useful in Word again.

Printed and typewritten text

Reads best. A smudge, a stamp or a handwritten note can leave a word uncertain, and a poor scan can be read wrongly without anyone noticing.

Headings and numbering

Not in the file. A converter that returns the page as floating text boxes leaves them for you to redo by hand.

Footnotes, definitions, tables

These need to come back as editable Word structure, not a picture of the page.

Three ways firms do it today

Retype it, convert it, or rebuild it.

Retype it

Careful retyping is accurate but slow, and every retyped word is a new chance for a mistake. Nothing marks the words a tired reader misread.

Run it through a basic converter

Fast, but pages may come back as floating text boxes, damaged text is left in the page, and whether the wording is checked varies by tool. See the comparison.

Rebuild it with LexForge

OCR reads the words and AI rebuilds the headings, numbering and structure. The draft is then checked against the words read from your file, and uncertain words are highlighted for a person to check.

What LexForge returns

An editable Word draft, ready to review.

  1. 01

    Upload your house style once

    Optional. A Word template or a well-formatted document teaches LexForge your headings, numbering and footnotes. How Reconstruct with House Style works, and what a house style is.

  2. 02

    Upload the scan

    A scanned PDF or a Word (.docx) file, up to 100 MB; a PDF can contain up to 200 pages. A Word file keeps its own clause numbering; your house style's numbering is applied to scanned PDFs only. Documents are stored and read in the UK, and nothing you upload is used to train AI models. Security page.

  3. 03

    Download the draft

    Headings, numbering, definitions and tables come back as editable Word structure. Footnote text is kept and returned as editable text in the body rather than as Word's linked footnotes. Every draft is checked against the words read from the source.

Before you rely on it

Review the highlighted words. Then the rest.

Every scan comes back as a review copy, with uncertain words highlighted for you to check against the original. The check confirms the draft matches what was read; it cannot prove that a poor scan was read correctly. How the wording check works.

Then read the rest against the original. Give most attention to names, dates, figures, clause numbers and defined terms, where one wrong character changes the meaning.

See it on a real page

A 1987 lease, before and after.

Scanned page of a typewritten 1987 lease, photocopied, with clause headings for Definitions and Repair and a footnote.
The scan: typewritten, photocopied, one word smudged.
The same lease page as an editable Word draft in a serif house style: numbered clauses, a footnote, and one uncertain word highlighted for review.
The Word draft: editable clauses, the footnote kept, the uncertain word highlighted. See both pages side by side and download both files.

Fictional specimen. Every name, party and clause is invented, and no client data is used.

Try it on a scan of your own.

The free trial needs no card.