Introduction to FileNet Capture ADR Definer - Fixed Form

Definer features an interface that allows configuration changes to be made quickly and includes an embedded Recognition engine that allows the effect of changes on the recognition process to be tested immediately.

There are two different types of processes available to configure the form definition.

1. Fixed Form

2. Free Form

Fixed Form is used to configure the structured documents while the Free Form is used to configure the unstructured or semi-structured documents. 

Below I have explained about the Fixed Form configuration. In the Fixed Form we need to define the fields and registration points which are became a reference points for the recognition to extract the data.

There are 2 different configuration files are used in the Definer.

1. Definition File (.idf)

2. Script File (.ifv)

Definition file specifies the location of the fields on each document type and details of expected character types, typefaces, noise removal strategies, etc. Specifies registration points used for document type identification and to correct for document misalignment. Specifies how fields are to be processed in Correction. Script file is used to transform the recognized data prior to output from Recognition.

Important Terminology:

Fields: An item of data that is to be captured is called a field. Fields can be of the following types: single line text, multi-line text, mark sense, mark grid, table or bar code.

Registration point: It is feature on the document used to recognize the document type. The position of all data fields is defined relative to the registration points. Registration point can be a corner mark, blob (for example logos), line and text.
Segmentation: It is the process of separating the text, marks or barcodes to be recognized from the background of the form and separating a field of text into individual characters.

Introduction to FileNet Capture ADR

Filenet Capture ADR (Advance Data Recognition)  is a set of modules that provide additional automatic data recognition and advanced keying (indexing and validation) functionality to Capture. ADR modules can be added in the capture process after the document assembly and the extracted data can be used for indexing process. Depending on the requirement the images are either the scanned copies or the imported images.

Advantages:

1. Indexing process is automated to reduce the cycle time.

2. Documents classification can be automated based on the key word search

There are 6 different modules in the ADR

1. Recognition

2. Document Review

3. Correction

4. Completion

5. Verification

6. Scripted Export

There are 8 different tools are used in the ADR

1. Definer

2. Recognition Trainer

3. Recognition Test Tool

4. Script Editor

5. Template Editor

6. Document Review Project Editor

7. Batch Compare

8. Transformation Studio

We will discuss about these tools in the next session.