Glossary main body

​

A

​

ABBYY FlexiLayout™ Studio

ABBYY FlexiLayout Studio is an application for creating formalized descriptions (FlexiLayouts) of semi-structured documents. The descriptions are then used by a documents processing application to capture data from the described documents.

​

layout alternative

A set of elements which describes a document subtype.

​

B

​

block

An area on a document image which outlines the possible location of a field.

​

building a FlexiLayout

When you build a FlexiLayout, FlexiLayout Studio checks the properties and relations you specified in the FlexiLayout for correctness.

​

C

​

classifier

A project in FlexiLayout Studio intended for the preliminary identification of the pages and selecting the appropriate FlexiLayout or layout alternative for them.

​

D

​

document class

A set of documents or pages that share several common characteristics.

​

dot (dt)

An abbreviation of document unit, equals 1/300 of an inch. A unit of measurement used to measure distances on an image. Does not depend on resolution. For a 300 dpi image, a distance of 1 dot equals 1 pixel.

​

E

​

element

A description of an image object which contains information about the type of the object, its properties, search area and location in relation to other objects.

​

F

​

flexible description

A formalized description of the document structure, designed to help detect fields. File format – *.afl.

​

H

​

hypothesis

An assumption made by the program that the object(s) detected on the image correspond(s) to the element of the FlexiLayout, i.e. meet(s) the search constraints and properties specified for the element.

​

M

​

matching a FlexiLayout with an image

A process of looking for the elements and blocks on the image described in the FlexiLayout.

​

multi-page sheet

The multitude of all pages in a document. a multi-page sheet is created by joining the pages of a document top down, without gaps or joints, with the left edge of all pages located on the same axis that goes through the point (0,0). The sequence of the pages in the sheet depends on their order in the batch. Two coordinate systems are used – global (goes through the entire document) and local (bound to a particular page. The only difference between the global and local coordinate systems is that the global system has parallel shifts, each page having its own shift.

​

N

​

null hypothesis

A hypothesis formulated by the program if it fails to find any objects corresponding to an optional element. The quality of the null hypothesis is set by the user when specifying the element’s properties.

​

O

​

optional element

An element that need not be present on the image. If the program fails to find an optional element, it will formulate a null hypothesis and continue matching the FlexiLayout. The quality of the null hypothesis is set by the user.

​

P

​

pre-recognition

The preliminary recognition of the image performed by the program during which it tries to detect elementary objects on the image.

​

prohibited element

An element which may not occur on the image. A chain of hypotheses that contains a prohibited element is discarded.

​

R

​

reference element

An element that is used for detecting other elements and marking up blocks.

​

reference layout

Manually selected blocks on the image to be used as a “model” layout.

​

region

An area on an image which consists of several rectangles. The bottom of one rectangle is part of the top of another rectangle.

​

required element

An element that must be present on the image. If the program fails to find a required element, it stops matching the FlexiLayout.

​

S

​

search area

An area on a document image where the program will look for objects described by the corresponding FlexiLayout element. Search areas are specified by the user in the Properties dialog box.