Text field

Add a Text field to a Document skill, set its data type, and configure recognition properties such as fonts, regular expressions, and date/number/money rules.

A Text field extracts a string value from a document — for example, a name, address, ID, or other text. The field’s data type (Text, Date, Number, or Money) determines how Vantage recognizes and validates the value.

Add a Text field

You can add a Text field in two ways.

Mark a region on the document image

Click a value (highlighted green on hover), or drag a rectangle around it. The new field appears in the data form.

Add an empty field, then mark its region

Click Add Field in the toolbar, then drag a rectangle around the value on the image. The data inside the region becomes the field value.

To rename a field, double-click the name in the data form, or click the name in the field properties. Triple-click to select the entire name. To open field properties, click Field options.

Add multiple regions to one field

Some values span multiple lines or pages, so a single field may need several regions.

To add multiple regions to a new field:

1. Add the field

   Use either method above.
2. Select additional regions

   Hold Shift and click or drag additional regions for the same field.

To add regions to an existing field, select the field in the data form, then click or drag its location on the image. If the value spans multiple words, select them all as a single region.

Regions can span multiple pages or sit inside another region. A nested region is highlighted in a darker color; when focused, it’s highlighted in yellow.

General properties

Property	Description
Field name	Unique within the skill. Cannot contain: . , / : * ? " < > |. Maximum length: 90 characters.
Data type	The kind of data the field contains. Affects recognition accuracy. See Data types for options.
Allow multiple items	Whether the field repeats (for example, multiple child names or account numbers).
Required field	If enabled and the field is empty after extraction, the document goes to manual review with an error.
Key field	Marks the value as searchable — used to look up documents.
Dimension field	Exposes the value as a reporting dimension in Skill Monitor.

Data types

Data type	Description
Text	May contain Latin and Cyrillic letters, digits, hieroglyphics, and special characters.
Date	A date and time in any format. Accepted separators: dot (.), space, hyphen (-), backslash (\), and forward slash (/).
Number	May contain digits, decimal separators, and the percent character (%). Accepted decimal separators: dot (.), comma (,), hyphen (-), equals sign (=), space. Accepted thousands separators: dot (.), comma (,), single quotation mark ('), space.
Money	A number value with a currency symbol. The symbol can appear before or after the amount.

The lowercase “l” (L), uppercase “I” (i), and digit “1” can look identical. In Number or Money fields, an ambiguous character is recognized as “1” because letters aren’t allowed.

Appearance settings

These properties describe the appearance of characters expected in the field.

• Text origin — Whether the field contains only printed characters, only handwritten characters, or both. If you add the field by dragging a rectangle, Vantage infers this value from the characters it finds. If you add the field with Add Field, the value defaults to Printed. See supported languages for handwritten text recognition.
• Eliminate field background — Improves recognition when the field has a frame, boxes for individual characters, or placeholder text. If you enable this option, upload the blank form document that serves as the background template and label the corresponding field on the blank form. The blank form appears in the Document Set, marked with an icon.
• Special fonts — Improves recognition accuracy when the field uses a specific font. You can select more than one font.

Handwritten text recognition is enabled for new Document skills by default. To toggle it, click the skill settings icon to the right of the skill name, open the Languages tab, and select or clear Handwritten in the Text Appearance section.

Supported fonts

Font	Description	Font sample
Fax	A font typically used by fax machines.
Gothic	Texts printed in Gothic type.
Index	A special set of characters that includes only digits written in ZIP-code style.
Matrix printer	Texts printed on a dot-matrix printer.
MICR CMC-7	A special MICR barcode font (CMC-7).
MICR E-13B	Numeric characters printed with magnetic ink. MICR (Magnetic Ink Character Recognition) characters appear on a variety of documents, including personal checks.
OCR-A	A monospaced font designed for optical character recognition. Widely used by banks, credit card companies, and similar businesses.
OCR-B	A font designed for optical character recognition.
Receipt	For text of low quality, typically in a monospaced or normal font used on receipts.
Typewriter	Typewritten texts.

Properties by data type

Additional properties depend on the data type.

Text

Value settings:

• Maximum length — The maximum number of characters allowed. If the extracted value exceeds this length, Vantage displays an error. If the process has a manual review stage, the document goes to manual review.
• Regular expression — A pattern that narrows the valid character set for the field, which can improve extraction accuracy. For example, you can force every character to be recognized as a digit, match a specific phone number format, or validate that a field contains a numeric weight with units.

Example 1 — Phone numbers like 1-(234)-567-8900 or 2 [phone]:

/^(1|2)(\-|\s)\([\d]{3}\)(\-|\s)[\d]{3}(\-|\s)[\d]{4}$/

Example 2 — Weight values like 50lb, 50lbs, 50Lb, 50Lbs, 50 lb, or 50 lbs:

/^[\d]*(\s)?(L|l)b(s)?$/

Regular expressions do not affect text recognition in PDF documents.

Date

Value may include settings:

• Time — Allow a time value. If disabled, time is not extracted.
• Day of week — Allow a day of the week in the field. If disabled, a day of the week is not extracted.
• Month by name — Allow the month to be spelled out as a word.

Acceptable order of components

Select one or more date formats: Day-Month-Year, Month-Day-Year, or Year-Month-Day. If the detected format doesn’t match any selected format, the document goes to manual review.

Acceptable date

Specify a valid date range as a number of months before and after the day the document was processed. Use integers. A rule checks whether the extracted date falls within the range; out-of-range dates go to manual review.

Number

Value settings specify what kind of number the detected value is (integer or decimal) and what number formats are accepted in the field. Values that don’t meet the requirements send the document to manual review.

• Integers only — The value must be an integer. Any separators in the detected number are treated as thousands separators.
• Fractional part may contain more than two digits — Enable when the decimal part is expected to have more than two digits. Accepted decimal separators: dot (.), comma (,), hyphen (-), equals sign (=), space.
• May have negative values — Allow negative values, denoted by a minus sign or brackets.
• May include ’%’ symbol — Allow a percentage character before or after the value.

Number must be within interval

Set a minimum and maximum value (integers or decimals, positive or negative). A rule checks whether the value falls within the range; out-of-range values send the document to manual review.

Money fields use the same properties as Number, except the percentage character is not allowed.

Related topics

Labeling documents

Guidelines for labeling structured and semi-structured documents during training.

Supported recognition languages

Full list of OCR languages supported across Vantage skills.