Classification Root Node - Infiniworx - Foundation 23.1 - Foundation 23.1 - AnyDoc - external

Infiniworx

Platform
AnyDoc
Product
Infiniworx
Release
Foundation 23.1
License

This tool performs image identification against a predefined set of forms.

To use Keyword Search, the workflow must have an engine tool prior to this tool.

Job Objects (In)

Description

OCR Job Object

Name of the OCR job object to be used by this tool.

Image Job Object

Name of the image job object to be used by this tool.

Text Job Object

Name of the text job object to be used by this tool.

Secondary Text Job Object

Name of the secondary text job object to be used by this tool.

Job Objects (Out)

Description

XML Result Object

Name of the XML result job object created by this tool.

Options

Description

System Location

Specifies the storage location for the classification system.

Database Build

Specifies whether the building of the classification database should take place automatically or manually.

Assign Batch to 1st Classified Type

When this option is set, the entire batch will be assigned to the first classified Document Group.

Use Context

If Yes, the previous and next image identification results are used to identify questionable images.

Maximum Page Input

Sets the maximum number of job pages used for document level classification.

Default Page Type

Sets the default page type when an image cannot be classified.

Default Document Type

Sets the default document type when an image cannot be classified.

Apply Defaults

Determines if post-classification default processing should be executed.

One Document Group Per Job

Specifies if each Infiniworx job should begin a new document group.

Maintenance

Description

Training

Click the Manage System button to open the image classification training area.

System Input

Description

Page Number

Data field containing the incoming page number.

Data Fields

Description

System

Links the system output of the tool to a data field.

Page Type

Links the page type output of the tool to a data field.

Document Type

Links the document type output of the tool to a data field.

Page Number

Links the page number output of the tool to a data field.

Match Percent

Links the match percent output of the tool to a data field.

Exception Count

Links the exception count output of the tool to a data field.

Tip:

To classify and OCR AnyApp data from an email body and other files such as an .XLS and .DOC email attachments, turn on the option "One Document Group per Job". This allows the .DOC file and the .XLS file to be classified correctly.

Note:

Content Analyst has been replaced with Brainware. If you are loading a workflow that was configured to use Content Analyst, the settings automatically change to Brainware. If the rate of classification decreases after upgrading to the Brainware engine, you should have at least ten images per page type in all match criterion that use the Brainware engine.