How does it know which answer belongs to which question?

From the geometry of the sheet: the position of the writing relative to the rule, the box and the label, and the numbering of the items. On a form where the questions run on as sentences, the answer is the writing inside the sentence, and it is returned against the printed wording that surrounds it.

Are ticks, crosses and circled options recognised?

Yes, and they are reported as the state of the field rather than as characters. A ticked box, a crossed box, a filled circle and a ring drawn round a printed word are all treated as a selection; a mark that sits between two options or that has been struck out again is flagged rather than assigned.

Can it tell an empty field from one it could not read?

These are reported differently. An empty field comes back as empty; writing that is present but illegible is marked as unread, so a person can go back to the image. Conflating the two is how partly completed forms turn into confident, wrong data.

What happens when the answer runs outside its box?

The writing is assigned to the field it started in, and the overflow is kept with it rather than split between two fields or moved into the answer below. Where a comb box has been ignored and a name written straight across the cells, the name is read as a word.

Can names and identifiers be kept out of the transcription?

Yes. You can ask for named fields to be redacted or replaced with a placeholder so that the structure and the substantive answers survive without the identity. This is worth doing on any batch of medical, benefit or membership forms before the text goes anywhere else.

English

Answers that stay attached to their questions

A form is two documents printed on one sheet: the questions, boxes and small-print instructions that were there before anyone touched it, and the answers somebody added afterwards. Read it as flat text and the two layers interleave into nonsense — a surname next to the words “Family name”, a tick with nothing to tick. Evidano keeps them apart, pairs each response with the field it belongs to, and tells you when a box was left empty rather than quietly skipping it.

Upload a page

Sample pages

A blank NHS combined pathology request form with tick boxes, a block-capitals box for the surname and green office-use panels — Sample 1. A blank combined pathology request form from Homerton University Hospital, photographed in 2020. Modern form furniture at its densest: a surname box marked Block capitals, an M/F choice, tick boxes for discipline and for ethnic origin arranged in two columns, an instruction printed sideways down the left edge, and a panel marked “For laboratory use”.

Referring G.P. or Consultant	PLEASE PRESS FIRMLY USING A BALL POINT PEN IF LABELS USED APPLY BELOW AND TO COPIES
Ward / Practice Address	Surname (Block capitals)	Date of Birth	Sex M / F
	Forename(s)	Unit Number
	NHS Number	Dr's Name Bleep No.
	Date and Time of Collection Hrs.	Date of last Blood Transfusion
Private ☐ CAT II ☐ NHS ☐ TRIAL ☐	Ethnic Origin (Not place of birth) N. European ☐ African ☐ Indian Subcontinent ☐ Other (Specify) ☐	Greek ☐ Turkish ☐ Chinese ☐ Afro/Caribbean ☐

A 1917 United States draft registration card with twelve numbered questions answered in ink and large clerical numbers written across it — Sample 2. The First World War draft registration card completed by Joseph F. Keaton — the film comedian Buster Keaton — on 5 June 1917. Twelve numbered questions, several with bracketed sub-labels under the rule; items 6, 9, 11 and 12 are left blank, the occupation runs over the end of its line, and a clerk has written the huge figures “28” and “1272” diagonally across the answers.

	Question	Answer
1	Name in full (Given name) (Family name)	2737 Joseph F Keaton
	Age, in yrs.	21
2	Home address (No.) (Street) (City) (State)	368 W 10 · Ny · Ny
3	Date of birth (Month) (Day) (Year)	10 · 4 · 1895
4	Are you (1) a natural-born citizen, (2) a naturalized citizen, (3) an alien, (4) or have you declared your intention (specify which)?	Native Born
5	Where were you born? (Town) (State) (Nation)	Picquy · Kan. · U.S.a
6	If not a citizen, of what country are you a citizen or subject?
7	What is your present trade, occupation, or office?	28 Motion Picture Perf.
8	By whom employed?	Rosco Arbucle
	Where employed?	43[illegible] Broway
9	Have you a father, mother, wife, child under 12, or a sister or brother under 12, solely dependent on you for support (specify which)?
10	Married or single (which)?	Single
	Race (specify which)?	Caucasian
11	What military service have you had? Rank; branch; years; Nation or State	1272
12	Do you claim exemption from draft (specify grounds)?

An 1894 printed application for a plumber’s licence in Seattle, completed in ink, with a red annotation added at the top left — Sample 3. An application for a plumber’s licence made to the Health Officer of the City of Seattle, 18 September 1894. The questions run on as printed prose with dotted rules for the answers, so the responses sit inside the sentences; the field “This Application is” was never completed, and the office has added “License No. 406. Issued Sept. 18th 1894” in red at the top left, beside the heading.

A partly completed 1941 United States individual income tax return, with pencil amounts in dollars-and-cents columns and four figures crossed out — Sample 4. Form 1040, the United States individual income tax return for the calendar year 1941, filled in partly in pencil. The name and address block is empty; amounts are entered against numbered items in split dollars-and-cents columns, four entries have been struck through and rewritten, and the boxes headed “Do not use these spaces” at the top right are reserved for the collector’s office.

Detail of a blank 1940 United States census population schedule showing multi-level column headings in very small type above rows of blank ruling — Sample 5. The left-hand half of a blank population schedule for the Sixteenth Census of the United States, 1940. Column headings are stacked three deep and carry their own instructions in type barely a millimetre high, the columns are numbered so the enumerator can find them again, and the supplementary questions printed at the foot of the sheet, below this detail, were asked only of the people written on lines 14 and 29.

Col.	Heading
6	[illegible]TA — Does this household live on a farm? (Yes or No)
7	NAME — Name of each person whose usual place of residence on April 1, 1940, was in this household. BE SURE TO INCLUDE: 1. Persons temporarily absent from household. Write "Ab" after names of such persons. 2. Children under 1 year of age. Write "Infant" if child has not been given a first name. Enter ⊗ after name of person furnishing information.
8	RELATION — Relationship of this person to the head of the household, as wife, daughter, father, mother-in-law, grandson, lodger, lodger's wife, servant, hired hand, etc.
A	CODE (Leave blank)
9	PERSONAL DESCRIPTION — Sex—Male (M), Female (F)
10	Color or race
11	Age at last birthday
12	Marital status—Single (S), Married (M), Widowed (Wd), Divorced (D)
13	EDUCATION — Attended school or college any time since March 1, 1940? (Yes or No)
14	Highest grade of school completed
B	CODE (Leave blank)
15	PLACE OF BIRTH — If born in the United States, give State, Territory, or possession. If foreign born, give country in which birthplace was situated on January 1, 1937. Distinguish Canada-French from Canada-English and Irish Free State (Eire) from Northern Ireland.
C	CODE (Leave blank)
16	CITIZENSHIP — Citizenship of the foreign born
17	RESIDENCE, APRIL 1, 1935 — City, town, or village having 2,500 or more inhabitants. Enter "R" for all other places.
18	COUNTY
19	STATE (or Territory or foreign country)
[illegible]	On a farm[illegible]

The two layers on a completed form

The printed layer is dense and highly structured. A form usually carries a title and a form number, a block of instructions in smaller type, numbered items, field labels with sub-labels in brackets underneath the rule (“(Given name)”, “(Street and number)”), comb boxes that take one character per cell, tick boxes and radio circles, rating scales, and one or more panels reserved for the office that will process the sheet. Some of the printed text is rotated ninety degrees along the edge; some of it is a conditional instruction that applies only to certain lines, as on a census schedule where supplementary questions are asked only of the people entered on two particular rows.

The response layer is whatever the person in front of the form did. Block capitals for a name, joined writing for the rest, a tick or a cross or a diagonal stroke or a circle round the chosen option, a figure written over another figure without the first being crossed out, a dash or “N/A” or nothing at all where a question did not apply. Answers routinely leave their boxes: a long address wraps into the field below, an explanation carries on up the margin with a bracket, an amount is written across the dollars-and-cents divider rather than either side of it.

Then there is everything added after the form was handed in. A rubber stamp with a date, a reference number written diagonally across the sheet in a different pen, an approval initialled in red, a coding mark made by a clerk preparing the data for punching, a note that the licence was issued and when. These belong to the file rather than to the respondent, and a transcription that treats them as answers will attach a clerk’s reference number to whichever question it happens to overlap.

Why ordinary OCR struggles here

The label and the answer are separate things

Plain text extraction returns the words in the order they appear on the page, which mixes the questionnaire with its responses. What you actually want is a pairing: item 7 asks for the present trade or occupation, the answer is “Motion Picture Perf”. Without the pairing you cannot load the sheet into a spreadsheet, and you cannot tell a printed example answer from a real one.

Empty boxes carry meaning

A blank field can mean the question did not apply, that the respondent refused, that the enumerator skipped it under an instruction, or that the form was never finished. Silently dropping empty fields destroys all four possibilities, and makes an incomplete return look like a complete one. Blanks have to be reported as blanks, and distinguished from fields the model could not read.

Marks are not characters

Ticks, crosses, dots, filled bubbles and circles drawn round a printed word are answers, but no letter corresponds to them. Add the human tendency to put the mark between two boxes, or to tick and then cross out, and the interesting cases are exactly the ones a character recogniser cannot represent at all.

Writing that will not stay in its box

Comb boxes assume one letter per cell and long names ignore them. An explanation runs past the ruled line into the next question. A pencilled correction sits above the figure it replaces. Deciding which field a stray line of writing belongs to needs the geometry of the blank form, not just the ink on this copy.

Who works with this material

Records teams digitising a back-file

Licence applications, permits, membership forms and registration cards sit in boxes because keying them costs more than they are worth one at a time. Field-and-value output turns a run of identical sheets into rows, and the exceptions — a form filled in wrongly, an unsigned declaration — surface instead of being averaged away.

Survey and evaluation teams

Paper questionnaires still come back from clinics, classrooms and doorsteps. What matters is that a rating is read as the point on the scale that was marked, that free-text comments stay attached to the question that prompted them, and that partially completed returns are visibly partial when they reach the analysis.

Genealogists and archive indexers

Census schedules, enlistment papers and registration cards are the backbone of family history, and their value depends on names, ages and places being read exactly. An indexer wants the enumerator’s own spelling, the crossings-out, and a flag on anything doubtful, not a tidied version.

Administrators handling sensitive returns

Medical request forms, benefit claims and consent forms carry identifiers that most downstream uses do not need. Being able to capture the clinical or operational fields while holding back names, numbers and dates of birth is often the difference between a usable workflow and one that cannot be approved.

Getting the best transcription

Step 1

Show the blank form first

If you have an unused copy of the same form, transcribe that before the completed ones. It gives you the printed layer on its own — every label, every instruction, the position of every box — so the completed sheets can be read as answers against a known template rather than deciphered from scratch each time.

Step 2

Ask for pairs, not paragraphs

Request the output as field and value, one per line or as JSON, and say what an untouched field should look like: an empty string, the word “blank”, or an explicit note that the enumerator was told to skip it. That single decision is what makes a stack of forms loadable into a spreadsheet.

Step 3

Spell out how marks should be reported

Say whether a tick, a cross and a circled option should all come back as “checked”, and what should happen when a mark straddles two boxes or an option is ticked and then struck out. Ambiguous marks are better reported as ambiguous than resolved by a coin toss.

Step 4

Decide about personal data before you start

Forms are the most identity-dense documents most people scan. Say in the prompt which fields should be redacted or replaced by a placeholder — name, address, date of birth, reference numbers — and check that they really are absent from the first few outputs before you run the batch.

Frequently asked questions

How does it know which answer belongs to which question?: From the geometry of the sheet: the position of the writing relative to the rule, the box and the label, and the numbering of the items. On a form where the questions run on as sentences, the answer is the writing inside the sentence, and it is returned against the printed wording that surrounds it.
Are ticks, crosses and circled options recognised?: Yes, and they are reported as the state of the field rather than as characters. A ticked box, a crossed box, a filled circle and a ring drawn round a printed word are all treated as a selection; a mark that sits between two options or that has been struck out again is flagged rather than assigned.
Can it tell an empty field from one it could not read?: These are reported differently. An empty field comes back as empty; writing that is present but illegible is marked as unread, so a person can go back to the image. Conflating the two is how partly completed forms turn into confident, wrong data.
What happens when the answer runs outside its box?: The writing is assigned to the field it started in, and the overflow is kept with it rather than split between two fields or moved into the answer below. Where a comb box has been ignored and a name written straight across the cells, the name is read as a word.
Can names and identifiers be kept out of the transcription?: Yes. You can ask for named fields to be redacted or replaced with a placeholder so that the structure and the substantive answers survive without the identity. This is worth doing on any batch of medical, benefit or membership forms before the text goes anywhere else.

Related scripts and pages

Handwritten ContentThe same handwriting away from the boxes: letters, diaries, notebooks and registers.Tables and Structured ContentRuled grids, stacked headings and continuation rows, where the shape of the page is the data.Official and Identity DocumentsCertificates, permits and identity papers, and how to handle the fields you would rather not keep.All English hands and document typesEvery English domain, from medieval minuscule to census schedules and screenshots.Image to TextSearch all supported languages, scripts and document types.

Turn a box of completed forms into rows

Upload a blank form and a filled one, choose Forms and Questionnaires, and check the field pairing before you run the rest of the batch.

	Tick Box	Specimen Type	DETAILS OF ANTIBIOTIC THERAPY
CHEMICAL PATHOLOGY
HAEMATOLOGY
MICROBIOLOGY

Item and Instruction No. INCOME
1. Salaries and other compensation for personal services, $ [cancelled: 3457.25] \3481.25/	Deductible Expenses (Attach itemized statement) $ _________		$ 3481	25
2. Dividends [cancelled: 42.06]			42	06
3. Interest on (a) bank deposits, notes, etc., $ _________ ; (b) corporation bonds, $ _________
4. Interest on Government obligations, etc.:
(a) From line (h), Schedule A, $ _________ ; (b) from line (i), Schedule A, $ _________
5. Rents and royalties. (From Schedule B)
6. Annuities
ITEMS 7, 8, AND 9, BELOW (AND PAGES 3 AND 4) NEED NOT BE CONSIDERED UNLESS YOU HAVE INCOME (OR LOSSES) IN ADDITION TO ITEMS ABOVE.
7. (a) Net short-term gain from sale or exchange of capital assets. (From Schedule F)
(b) Net long-term gain (or loss) from sale or exchange of capital assets. (From Schedule F)
(c) Net gain (or loss) from sale or exchange of property other than capital assets. (From Schedule G)
8. Net profit (or loss) from business or profession. (From Schedule H)
(State total receipts, from line 1, Schedule H, $ _________ )
9. Income (or loss) from partnerships; fiduciary income; and other income. (From Schedule I)
10. Total income in items 1 to 9			$ 3523	31
DEDUCTIONS
11. Contributions paid. (Explain in Schedule C)			$ 19	00
12. Interest. (Explain in Schedule C)			216	00
13. Taxes. (Explain in Schedule C)			170	76
14. Losses from fire, storm, shipwreck, or other casualty, or theft. (Explain in Schedule C)
15. Bad debts. (Explain in Schedule C)
16. Other deductions authorized by law. (Explain in Schedule C)
17. Total deductions in items 11 to 16	[cancelled: 405]	[cancelled: 76]	405	76
18. Net income (item 10 minus item 17)			$ 3117	55

19. Net income (item 18 above)	$ 3117	55
20. Less: Personal exemption. (From Schedule D-1) $ 1500 00
21. Credit for dependents. (From Schedule D-2) 800 00	2300	00
22. Balance (surtax net income)	$ 817	55
23. Less: Item 4 (a) above $ _________
24. Earned income credit. (From Schedule E-1 or E-2) 311 75	311	75
25. Balance subject to normal tax	$ 505	80

26. Normal tax (4% of item 25)	$ 20	23
27. Surtax on item 22. (See Instruction 27)	49	05
28. Total (item 26 plus item 27)	$ 69	28
29. Total tax (item 28 or line 16, Schedule F)	$ 69	28
30. Less: Income tax paid at source $ _________
31. Income tax paid to a foreign country or U.S. possession. (Attach Form 1116) _________
32. Balance of tax (item 29 minus items 30 and 31)	$ 69	28

Answers that stay attached to their questions

Sample pages

Evidano Transcription

Evidano Transcription

Evidano Transcription

Evidano Transcription

Evidano Transcription

The two layers on a completed form

Why ordinary OCR struggles here

The label and the answer are separate things

Empty boxes carry meaning

Marks are not characters

Writing that will not stay in its box

Who works with this material

Records teams digitising a back-file

Survey and evaluation teams

Genealogists and archive indexers

Administrators handling sensitive returns

Getting the best transcription

Show the blank form first

Ask for pairs, not paragraphs

Spell out how marks should be reported

Decide about personal data before you start

Frequently asked questions

Related scripts and pages

Turn a box of completed forms into rows

Company

About

Preview Evidano

Account

Newsletter