Math OCR: Image to LaTeX
Scan a textbook page or paper and get every displayed formula back as native LaTeX. Edit the source with a live rendered preview, then export a compile-ready .tex file — headings, text and tabulars included.
How it works
- 1
Upload the page — a photo, scan or PDF of printed math.
- 2
Formulas are detected as separate blocks and recognized as native LaTeX.
- 3
Edit with the live preview if needed, then export .tex, Markdown or HTML.
Why OhMyOCR
Native LaTeX out
Displayed equations come back as LaTeX source, not pictures of math.
Live rendered preview
Edit a formula and watch the rendered version update as you type — catch a wrong subscript before it hits your document.
Compile-ready .tex export
One click produces an article-class .tex with sections, escaped text, tabular tables and \[…\] display math.
Whole-document context
Formulas are recognized alongside the surrounding text and tables, each linked to its exact spot on the page.
Why math is the hardest OCR — and why LaTeX is the right output
Ordinary OCR reads left to right; mathematics is two-dimensional. Superscripts, subscripts, fractions, radicals, integral limits and matrices all encode meaning in vertical position and size — flatten x² into x2 and the statement is simply wrong. Math OCR has to recover that structure, not just the symbols.
That is why the output format matters: LaTeX is the notation that preserves structure losslessly and compiles anywhere — papers, theses, Overleaf, Jupyter, Anki cards, MathJax and KaTeX on the web. OhMyOCR recognizes displayed formulas as native LaTeX source rather than pictures of equations.
Trust, but verify — with a live preview
A single wrong subscript changes the meaning of a formula, and raw LaTeX is hard to proof by eye. The workspace pairs every recognized formula with a live rendered preview: compare it against the source region, and if something is off, edit the LaTeX and watch the render update as you type.
For whole documents — a scanned problem set, lecture notes, a paper chapter — formulas are recognized alongside the surrounding text and tables, and the one-click .tex export builds a compile-ready article: sections, escaped text, tabulars and display math in place.
Frequently asked questions
How do I convert an image of an equation to LaTeX?
Upload the page to OhMyOCR, open the Formulas tab, and each displayed equation appears as LaTeX with a rendered preview. Copy the source or export the whole document as .tex.
Can I edit the recognized LaTeX?
Yes — double-click a formula block to edit its source with a live KaTeX preview underneath, so you see the rendered result while you type.
Does it export a full .tex document?
Yes. The LaTeX export builds an article-class document: headings become sections, tables become tabulars, and display formulas are placed in math environments.
Does it work on handwritten math?
Printed formulas are the primary target. Handwritten regions are flagged for review, and results vary with legibility — the inline editor with live preview makes fixes quick.
More free OCR tools
Image → Text
Image to Text Converter
PDF → Text
PDF to Text Converter (OCR)
Document Parsing
Document Parsing OCR
Image Translation
Image Translator with OCR
Image → Excel
Image to Excel Converter
Handwriting → Text
Handwriting to Text Converter
Screenshot → Text
Screenshot to Text
Image → Word
Image to Word Converter
PDF → Markdown
PDF to Markdown Converter
Receipt → Text / Excel
Receipt OCR: Scan Receipts to Text or Excel
Try it on your own file
Free to start, no credit card, results you can verify line by line.