PNG to Excel XLSX converter

PNG to XLSX converted a receipt image into one worksheet with numeric amount cells and minus signs for parenthesized credits.

Converted with AI Deep Read · input deleted within 24 h
Free: 5 conversions a day · 5 MB each
Higher limits →

From real runs

What you get — and what changes

Element	Result	What happens
Worksheet creation	Kept	The output was a valid XLSX workbook with one sheet named by the converter pipeline.
Receipt title	Changed	Store name and register text became single-column rows above the detected table instead of worksheet metadata.
Item table	Kept	Item, Qty, and Amount headers were detected, and the main product rows landed in separate columns.
Negative values	Changed	Parenthesized amounts were normalized to numeric negatives, changing '(4.20)' to -4.2 and '(3.00)' to -3.
Blank quantity rows	Changed	Tax and coupon rows kept their amounts, but empty Qty cells made those rows visually ragged in the sheet XML.
Payment details	Changed	Card authorization and reimbursement note were appended as single-column rows below the transaction table.
Runtime	Kept	The PNG receipt produced a 16.4 KB XLSX in 6.7 seconds and used one credit for the image.

Worksheet creation Kept
The output was a valid XLSX workbook with one sheet named by the converter pipeline.
Receipt title Changed
Store name and register text became single-column rows above the detected table instead of worksheet metadata.
Item table Kept
Item, Qty, and Amount headers were detected, and the main product rows landed in separate columns.
Negative values Changed
Parenthesized amounts were normalized to numeric negatives, changing '(4.20)' to -4.2 and '(3.00)' to -3.
Blank quantity rows Changed
Tax and coupon rows kept their amounts, but empty Qty cells made those rows visually ragged in the sheet XML.
Payment details Changed
Card authorization and reimbursement note were appended as single-column rows below the transaction table.
Runtime Kept
The PNG receipt produced a 16.4 KB XLSX in 6.7 seconds and used one credit for the image.

Sample conversions

Receipt table image

Input: PNG receipt with Item, Qty, Amount columns, two merchandise rows, a returned binder, tax, coupon, total, and payment note.
Output: XLSX rows included typed numbers for quantities and amounts. Parentheses became minus signs, while tax and coupon rows had empty Qty cells.

Schedule table image

Input: PNG page with a five-column sampling schedule under two columns of prose.
Output: Deep Read can find the table, but prose above or below it may become extra worksheet rows that should be removed before analysis.

A real PNG → Excel XLSX run

We converted our PNG sample (219 KB) with AI Deep Read under AI Deep Read on 2026-09-11. It took 9.5 s and produced a 17 KB Excel XLSX file, 92% smaller than the input. The engine raised 1 warning, listed below.

Input · sample.png · 219 KB

1240 × 1754 px, 8-bit, colour type 2

Width: 1,240
Height: 1,754
Encoding: 8-bit, colour type 2

Output · sample.xlsx · 17 KB

Workbook with 1 sheet (Extracted); first sheet 15 rows, 27 cells, 0 formulas, header filter, fitted column widths

Sheets: 1
Sheet names: Extracted
Rows: 15
Cells: 27
Formulas: 0
Header filter: yes
Column widths: fitted

AI Deep Read read 1 page; 1 credit per page

Is your file a scan?

PNG table extraction spends 1 Deep Read credit per image and asks the model for pipe tables before XLSX materialization. Review every numeric cell because OCR normalized accounting parentheses and trimmed trailing zeros in the tested receipt.

Options and when to change them

extractTablesAsGfm: Keep this on so Deep Read emits pipe tables that our table engine can turn into worksheet rows.
preserveLayout: Use it for images where row grouping is more important than stripping surrounding notes.
languageHint: Set it when merchant names, item labels, or column headers are in a known non-English language.

Do it yourself

Tesseract + pandas 2.3

bash

tesseract receipt.png stdout --psm 6 > receipt.txt
python3 - <<'PY'
import pandas as pd
rows = [['Item','Qty','Amount'], ['Printer paper A4',2,18.90]]
pd.DataFrame(rows[1:], columns=rows[0]).to_excel('receipt.xlsx', index=False)
PY

The pandas step needs reviewed rows; plain OCR text is not enough to infer every table cell automatically.

PNG to Excel XLSX by API or MCP

The HTTP API and the MCP server run the exact engine this page uses (AI Deep Read); the response carries the same warnings the web converter shows. Check support first with GET /api/v1/pairs?from=png&to=xlsx.

curl

curl -X POST https://filetypeconverters.com/api/v1/convert \
  -H "Authorization: Bearer $FTC_API_KEY" \
  -F "file=@input.png" -F "from=png" -F "to=xlsx" \
  -F "deepRead=true" \
  --output output.xlsx

API reference

When this is the wrong conversion

If you want a narrative transcript of a screenshot, use /convert/png-to-md or /convert/png-to-txt instead of a workbook.
If the source is already an Excel export displayed as an image, ask for the original XLSX to preserve formulas.
If all you need is comma-separated text for an import, /convert/png-to-csv is smaller but less faithful on this receipt sample.

PNG to Excel XLSX questions

Are numbers typed as Excel numbers?

Yes for the tested quantities and amounts. The sheet XML stored 2, 18.9, 12.49, -4.2, -3, and 26.43 as numeric cells rather than shared strings.

Why did 18.90 become 18.9?

The spreadsheet writer stored the value as a number, so trailing zeros are not part of the raw cell value. Apply currency formatting in Excel if fixed cents are required.

What happens to receipt notes below the table?

They are appended as worksheet rows, not discarded. Delete or move those rows before importing into an accounting system.