OCR PDF to Excel: Convert Scanned and Image PDFs to Excel
A scanned or photographed PDF is just a picture, so a normal converter reads nothing from it. PDFXLSX runs OCR (optical character recognition) to read the numbers and tables off the image first, then writes a clean Excel file with the columns lined up and the figures kept numeric. Scans, photos, and image-based PDFs all work. Drop a file on the right to convert your first one free.
Works in any browser on Windows, Mac, and phones. First conversion is free, no software to install, and files are deleted after processing.
Drop your PDF here or click to browse
PDF files up to 50MB
A real editable .xlsx from a scan, not a picture in a cell. First file free.
The short answer
Last updated July 2026To OCR a scanned PDF into Excel, run the file through an OCR-based converter that reads the text off the image, rebuilds the table structure, and writes real editable cells. A plain PDF-to-Excel tool cannot do this because a scan holds no selectable text, only a picture. PDFXLSX applies OCR automatically, keeps numbers numeric so columns still total, and outputs XLSX or CSV. Scans, photos, and image-based PDFs all work in the browser, with no software to install.
OCR
Reads scans and photos
Editable
Real cells, not an image
Numeric
Amounts stay numbers
No install
Runs in your browser
Why a scanned PDF needs OCR before it reaches Excel
There are two kinds of PDF that look identical on screen. A digital PDF, exported straight from software, holds real text you can select and copy. A scanned PDF is a photo of a page: every number on it is part of an image, so there is no text to pull. Drop that scan into an ordinary converter and you get an empty sheet or a single image stuck in one cell, because there is nothing for it to read.
OCR, short for optical character recognition, is the step that closes that gap. It looks at the picture, recognizes each character and figure, and turns the image back into real text. PDFXLSX runs OCR on every page that needs it, finds the actual table in the recognized text, and writes each value into its own cell. A photographed bank statement comes out as rows and columns you can sort and total, not a flat image.
You see the converted table before you download, so you can check the figures against the original. Want the step-by-step version of this workflow? See how to convert a scanned PDF to Excel, or for getting fully editable cells out of a scan, convert a PDF to editable Excel.
Date Description Amount 03/05 Deposit ACH 2210 5,210.00 03/09 Vendor payment -318.74 03/14 Service fee -18.00 03/22 Invoice 4471 2,640.25
From an image, OCR recovers the date, description, and amount as separate columns, with negatives kept negative and amounts stored as numbers you can sum, not text trapped in a picture.
How accurate is OCR, honestly
On a clean scan, modern OCR reads roughly 98 to 99 percent of characters correctly, and on a sharp digital-quality image it is usually higher. That is good, but it is not perfect, and with financial data the few percent that can slip matters. So the honest rule is simple: OCR does the heavy lifting, and you spend a minute checking the result instead of an hour retyping the whole page.
The mistakes OCR makes are predictable, which makes them easy to catch. It confuses characters that look alike: a lowercase l, the digit 1, and a capital I; the digit 0 and the letter O; and the pair r n read as a single m. On a faint or skewed scan it can also miss a minus sign or a decimal point. The fix is to scan or photograph at 300 dpi or better, keep the page straight and well lit, then check the preview before you download.
The fastest accuracy check on financial documents is to foot the totals: sum the amount column in Excel and confirm it matches the printed total on the statement. If it ties, the figures came across clean. For more on keeping figures exact once they are in the sheet, see the accurate PDF to Excel converter.
Get the best OCR result
- 1. Scan or photograph at 300 dpi or higher. Low-resolution images are the single biggest cause of OCR errors.
- 2. Keep the page flat and straight. A skewed or curled scan shifts characters and confuses column edges.
- 3. Use good, even light with no shadow across the figures when you shoot a page with a phone.
- 4. Check the preview and foot the totals. A 30-second tie-out beats trusting any tool blind.
No OCR engine is perfect on every page, which is exactly why the preview is there: you verify before anything lands in your books.
What the OCR PDF to Excel converter does
The details that turn a flat scan into a spreadsheet you can actually work in.
Reads scans and photos
Built-in OCR recognizes text on a scanned page, a photographed document, or any image-based PDF, so a file with no selectable text still converts to real rows and columns.
Keeps the table structure
After OCR, the engine maps the recognized text back into the original grid, so a date, description, and amount land in three separate columns, not one merged blob.
Numbers stay numeric
Recognized amounts are written as real numbers, with negatives and decimals intact, so a SUM works the moment the file opens instead of returning zero on text that only looks like a figure.
Batch a stack of scans
Most desktop OCR runs one file at a time. Send a folder of scanned statements through the batch converter and get a separate Excel file for each, which is the usual need for a full year.
Preview before you trust it
OCR is strong but never perfect, so you see the recognized table on screen first. Check the figures against the scan, then download. No guessing what landed in the file.
Private and secure
The scans you most need converted are often the most sensitive. Uploads are encrypted in transit and at rest, processed in isolation, and deleted automatically once your file is ready. Nothing is kept or reused.
How to OCR a PDF to Excel
Three steps, with a chance to check the figures before they go anywhere.
Upload the scanned PDF
Drag the file into the box at the top of the page or pick it from your device. Scans, phone photos, and image-based PDFs all work, and you can send several at once.
OCR reads the page
The engine recognizes the characters in the image, rebuilds the table, and writes each value into its own cell with amounts kept numeric. No retyping, no manual columns.
Check, then download
Review the recognized table, foot the totals against the scan, then download a clean .xlsx or .csv. Your file is deleted right after processing.
What people OCR into Excel
Most OCR jobs are paper or scanned financial documents that someone needs as workable data.
Scanned bank statements
Older or mailed statements arrive as scans. OCR pulls the transactions into rows you can reconcile.
Receipts and photos
Phone snaps of receipts are pure images. OCR turns them into expense rows for a report or a script.
Scanned invoices
Supplier invoices that came in on paper convert to line items you can load into AP or a report.
Credit card statements
Photographed or scanned card statements become charges you can categorize and post.
Utility bills
Scanned bills turn into a clean table for tracking usage, cost, and allocations over time.
Printed reports and ledgers
A printed general ledger or financial report scans straight into data you can analyze.
Working through a backlog of scans? See the workflows for accountants, bookkeepers, and finance teams. On a Mac with a stack of scanned files? The Mac converter runs OCR in the browser with nothing to install.
How to tell if your PDF is scanned or digital
This decides whether OCR is even needed, and the test takes two seconds. Open the PDF and try to select a number with your cursor. If the text highlights and you can copy it, the file is a digital PDF with a real text layer, and it converts without OCR. If your cursor only draws a box and nothing highlights, the page is an image, and OCR is what makes it readable.
You do not have to run that test yourself before uploading. PDFXLSX detects which pages have a text layer and which are images, and applies OCR only where it is needed. A file that mixes both, say a digital export with a scanned page stapled in, is handled page by page. Either way you get one clean Excel file at the end.
If your PDF is already digital and you just want a faster, cleaner conversion, the general PDF to Excel converter covers it, and you can still export to CSV for importing into other software. For the trickiest scans, the guide to converting a scanned PDF to an editable Excel file walks through the cleanup.
Ways to OCR a PDF to Excel, compared
An honest look at what each method costs you in money, setup, and cleanup.
| Method | OCR built in? | Keeps columns? | Notes |
|---|---|---|---|
| Copy and paste from the PDF | No | No | There is no text on a scan to copy, so you get nothing. On a digital PDF it collapses into one column. |
| Excel Data, From PDF | No | Sometimes | The built-in import reads digital PDFs only, has no OCR, and is Windows and recent Microsoft 365 only. |
| Adobe Acrobat Pro | Yes | Usually | Has OCR and export, but needs a paid subscription and runs one file at a time on the desktop. |
| Open-source OCR plus a script | With setup | With tuning | Powerful and free, but it takes installs, libraries, and per-layout tuning. Overkill for a few files. |
| PDFXLSX in your browser | Yes | Yes | OCR on scans, real columns, numbers numeric, batches files, and shows the result so you can check it first. |
No OCR tool is perfect on every page, which is why the preview matters: you confirm the figures before they reach your books. Switching from a desktop tool? See how we compare with ABBYY FineReader and Adobe Acrobat.
OCR PDF to Excel: common questions
Upload the scanned PDF into the converter at the top of this page. It runs OCR to recognize the text in the image, rebuilds the table, and lets you check the preview before you download a clean .xlsx or .csv. Nothing installs, and a scan, a phone photo, or an image-based PDF all work. For the longer walkthrough, see how to convert a scanned PDF to Excel.
Yes. OCR is what makes a scanned or image PDF convertible at all. It recognizes the characters in the picture and turns them back into real text, which the converter then arranges into rows and columns in Excel. Without OCR, a scan is just an image and produces an empty sheet. Upload your file above to see your specific document recognized and converted before you download.
On a clean scan, OCR typically reads 98 to 99 percent of characters correctly, and a sharp digital-quality image does better. It is accurate but not flawless, so check the result on financial data. Most errors are predictable look-alikes, like 1 versus l or 0 versus O, which makes them easy to spot. Scan at 300 dpi or higher, then foot the total in Excel against the printed total to confirm the figures came across clean.
No. Excel has no OCR. Its built-in Get Data, From PDF feature reads only digital PDFs with a real text layer, and it is limited to Windows on recent Microsoft 365 builds. A scanned or image PDF returns nothing because there is no text for Excel to find. You need an OCR step first: this converter recognizes the scan and hands Excel a finished spreadsheet with the cells already filled in.
OCR stands for optical character recognition: software that looks at a picture of text and works out which characters it shows. A scanned PDF is a photo of a page, so the numbers on it are part of an image with no underlying text. OCR reads that image and recreates the text, which is what lets a converter put each value into its own Excel cell. Without it, a scan cannot become editable data.
Open the PDF and try to select a number with your cursor. If the text highlights and copies, it is a digital PDF with a real text layer and converts without OCR. If your cursor only draws a box and nothing highlights, the page is an image and needs OCR. You do not have to check manually before uploading: the converter detects image pages and applies OCR only where it is needed, even in a file that mixes both.
More PDF to Excel options
PDF to Excel Converter: Convert PDF to Excel Online
Convert PDF to Excel online with a converter built for business. Keeps tables intact and numbers numeric, runs OCR on scans, exports clean XLSX or CSV.
FeaturesAI PDF to Excel Converter: Convert PDF to Excel With AI Accuracy
Convert PDF to Excel with an AI converter that reads tables and scanned files, keeps numbers numeric, and exports clean XLSX or CSV. First file free.
FeaturesConvert PDF to XLSX Online With Real Cell Structure
Convert PDF to XLSX online into a native Excel file with real cell structure: numbers numeric, dates as dates, tables aligned. OCR included, first file free.
FeaturesPDF Table Extractor: Extract Tables From PDF to Excel
Extract tables from PDF to Excel automatically. A PDF table extractor that keeps rows and columns aligned, handles merged and multi-page tables, and reads scans.
OCR your PDF to Excel now
Drop a scanned or image PDF at the top of the page, let OCR read it, check the figures, and download a clean Excel file. Your first conversion is free. Need a plain import file instead? Export to CSV, or pull just the grids with the PDF table extractor.