Tungsten Automation Transformation Designer Help
  • Welcome
  • Overview
    • Capture paper documents
      • Paper and print
      • Drop-out colors
      • Field positioning
  • Transformation Designer mode
    • Limited to online learning
  • Use Transformation Designer
    • Connect to Tungsten TotalAgility
    • Manage the user interface
      • Transformation Designer ribbon
        • File menu
        • Project tab
        • Documents tab
        • Design tab
        • Process tab
        • View tab
      • Project Tree window
        • Project Class shortcut menus
        • Additional Project Tree shortcut menus
      • Project Tree selection behavior
      • Work with windows
      • Revert the layout
      • Minimize the Ribbon
      • Manage the Quick Access toolbar
      • Documents window
        • Toolbar in the Documents window
        • Shortcut menus for documents sets and subsets
        • List View in the Documents window
        • Hierarchy View in the Documents window
        • Thumbnail View in the Documents window
      • Document Viewer modes
        • Document Viewer
        • Document Viewer (table mode)
        • Document Viewer (zone mode)
    • Create a new project
    • Pass XValues to a Transformation activity
    • Export database project to file-based project
    • Import a file-based project
    • Open an existing project
    • Save a project
    • Configure Transformation Designer options
    • View project details
    • Project security
      • Read and write protect a project
      • Project protection
        • Protect a project
        • Unprotect a project
        • Locators and protected projects
        • Training documents and protected projects
    • Project upgrades
      • Merge training sets manually
      • Merge project with local changes to new version
    • Deployment and staging
      • Configuration setting preservation
      • Centralized relational database connections
    • Manage document sets
      • Preconfigured document sets
        • Classification set
        • Extraction set
        • Table Extraction Set
        • Exclude training document sets from database
        • Selection document set
        • New Samples document set
          • Sort new samples for vendor name and ID
      • Custom document test sets
        • Test sets
        • Attach a test set or benchmark set to a project
        • Benchmark document sets
        • Change a test set to a benchmark set
      • Document subsets
        • Default document subset
        • All documents subset
      • Upgraded projects and document set conversion
        • Extraction training set conversion
        • Classification training set conversion
        • Convert a New Samples database
      • Use document set to configure the project hierarchy
      • Document set attachment
      • Document set views
        • Switch the document set view
        • Documents List View
          • Manage columns in the list view
          • Sort documents by columns in the List View
          • Filter columns in the List View
        • Documents Hierarchy View
        • Documents Thumbnail View
          • Classify documents using the Thumbnails View
          • Delete pages using the Thumbnails View
          • Merge documents using the Thumbnails View
          • Split a document using the Thumbnails View
          • Move pages using the Thumbnails View
          • Rotate pages using the Thumbnails View
          • Edit content in the Thumbnail View
        • Custom filters in List View and Thumbnail View
        • Perform document recognition
        • Assign a class to documents
        • Classify documents
        • Perform document extraction
        • Process documents
        • Clear classification and extraction data from documents
        • Load classification and extraction data from documents
        • Add documents to the selected class for classification training
        • Add documents to the selected class for extraction training
        • Add documents to the selected class for table extraction training
        • Edit fields causing extraction issues
        • Open a document in the Document Viewer
        • Open a document in Windows Explorer
        • Open a document in XDoc Browser
      • Documents and clustering
        • Configure and perform clustering
        • Clustering keyboard shortcuts
      • Process new samples
        • Refresh New Samples
        • Import extraction online learning data
        • Download new samples from the server
      • Add a custom document set for testing
      • Convert a custom test set into a benchmark set
      • Set a default document subset
      • Add a document subset
      • Duplicate a document subset
      • Split a document subset
      • Add documents to a document subset
      • Add documents to a document subset using drag-and-drop
      • Delete documents from a document subset
      • Rename a document subset
      • Save a document subset
      • Copy documents using drag-and-drop
      • Move documents using drag-and-drop
      • Set a document set as the classification training set
      • Set a document set as the extraction training set
      • Set a document set as the Table Extraction Set
      • Exclude a document subset from a training set
      • Black and white conversion
        • Convert documents to black and white
      • Remove a document subset
      • Work with multiple document sets
      • Remove a document set
    • Manage recognition
      • Optical Character Recognition (OCR)
      • Optical Mark Recognition (OMR)
      • What is an XDoc?
      • Recognition engines
        • Azure AI Document Intelligence recognition engine
        • OmniPage recognition engine
          • OmniPage Asian OCR
        • Tungsten Clarity recognition engine
          • Tungsten Clarity using Google Vision
          • Tungsten Clarity image guidelines
        • FormXtra recognition engine
          • Language support for FormXtra zone field types
          • Writing styles, field type, and language support
        • A2iA recognition engine
        • FineReader recognition engine
        • RecoStar recognition engine
      • Recognition profile types
      • Recognition profiles
        • Default recognition profiles
        • Page recognition profiles
          • Add an Azure AI Document Intelligence page recognition profile
          • Add a mixed print page recognition profile
          • Add an OmniPage page recognition profile
          • Add a Tungsten Clarity page recognition profile
        • Zone recognition profiles
          • Add an Azure AI Document Intelligence zone recognition profile
          • Add and OmniPage zone recognition profile
          • Add a FormXtra zone recognition profile
          • Add an OMR recognition profile
          • Add a Tungsten Clarity zone recognition profile
        • Set a default recognition profile
        • Work with recognition profiles
      • Preconfigured recognition profiles
      • Zone recognition and printer types
        • OmniPage printer type mappings for deprecated engines
      • Recognition content types for zones
        • Alphanumeric content type
        • Numeric and amount content types
      • Substitute common OCR misreads
      • Determine the optimized threshold for handwritten text
      • Paragraph detection
        • Paragraphs and the Classification Locator
        • Scripts and paragraph detection
        • Enable paragraph detection
        • Train paragraphs
    • Manage tables
      • Which locator to use for table extraction?
      • The column pool
        • Global columns
        • User-defined columns
        • Work with user-defined columns
      • Table models
        • Work with table models
      • Table header packs
        • Work with table header packs
    • Manage table detection
      • Enable table detection for a class
      • Use table detection results
      • Add documents to Table Extraction Set
      • Detect tables for one or more documents
      • Table training documents
        • Edit a table training document
      • Train a project for table detection
      • When to retrain a project for table detection
    • Manage formatters
      • Work with formatters
        • Add an amount formatter
        • Add a date formatter
        • Add a percentage formatter
        • Add a script formatter
      • Assign a formatter to a field
    • Manage image cleanup
      • Image cleanup methods
      • Layer order
      • Work with image cleanup profiles
    • Manage dictionaries
      • Dictionary replacement text
      • Dictionaries and regular expressions
      • Sample dictionaries
      • Add a dictionary
      • Work with dictionaries
      • Configure a dictionary to update automatically
      • Manually update a dictionary from source
    • Manage databases
      • Fuzzy databases
        • Fuzzy database CSV and text file formats
        • Local fuzzy database automatic updates
        • Load a local fuzzy database in memory
        • Fuzzy database processing and optimization
        • Local fuzzy database column header names
        • Fuzzy database field delimiter characters
        • Fuzzy database characters to ignore
        • Fuzzy databases, fields, and documents
        • Fuzzy databases and filtering
        • Add a local fuzzy database
        • Import a local fuzzy database
        • Add a remote fuzzy database
        • Configure load balancing and high availability for remote fuzzy databases
      • Relational databases
        • Access rights for an Oracle database
        • Access rights for a Microsoft SQL Server database
        • Add a relational database connection
          • Configure a Microsoft SQL Server relational connection
          • Configure an ODBC relational connection
          • Configure an Oracle database connection
        • Relational database authentication
        • Create a relational database
      • Associative search databases
        • Associative search vs. fuzzy databases
        • Add an associative search database
      • Rename a database
      • Delete a database
    • Manage service endpoints
    • Image rotation
      • Configure image rotation
      • Rotation and mixed print recognition
    • Supported file types
      • Image files
        • TIFF image files
        • JPEG image files
        • PNG image files
      • Text files
      • PDF files
      • Color images
      • Black and white images
      • Configure color conversion to black and white
      • Reset black and white images
    • Project validation
      • DocAI solution projects
    • Name conventions
    • Manage country-specific settings
      • Projects and country-specific settings
      • Extraction and countries
      • Set the project design language
      • Configure countries and tax codes
      • OmniPage language mappings for deprecated engines
    • Word separation characters
    • Regular expressions
    • Manage string substitutions
      • Add a string substitution
      • Modify a string substitution
      • Delete a string substitution
      • Import a string substitution
      • Export a string substitution
    • Manage scripts
      • Script programming
        • Special characters in script
        • Scripts on project class level
        • Scripts on class level
      • Script resources
      • Manage script resources
      • External script variables
      • Manage script variables
      • Change the value of a script variable
      • Automatically export scripts
    • Manage natural language processing
      • Natural Language Processing engine
      • Custom entities
        • Custom entity folder structure
        • Custom entity file format
        • Custom entities sample in production
        • Create a custom entity file
        • Edit a custom entity file
      • Custom sentiments
        • Add custom sentiments
    • Test and optimizing a project
      • Preliminary tests
        • Preliminary classification testing
        • Preliminary extraction testing
        • Preliminary combined classification and extraction testing
        • Test runtime script events
        • Other preliminary tests
      • Normalize the image source file structure
    • Keyboard shortcut keys
    • Log files
      • Application log files
        • Application log file contents
      • Transformation Designer logs
        • Configure Transformation Designer logging
    • Project Settings general settings
  • Set up classification
    • Manual versus automatic classification techniques
    • Project-level vs. class-level classification
    • Configure project-level classification
    • Classes and the class tree
      • Define the default classification result
      • Manage classes
        • View class contents
        • Work with classes
        • Bulk edit multiple selected classes
    • Configure class details
      • Configure other classification settings
    • Classification and the order of processing
    • Layout classification
      • Layout classifier
        • Initialize and configure the layout classifier
        • Enable layout classification training for a class
        • Train the layout classifier
    • Content classification
      • Adaptive Feature Classifier
        • Enable content classification training for a class
        • Configure the Adaptive Feature Classifier
        • Thresholds, precision, and recall
        • Enable auto optimization and improve classification
      • Text classifier
      • Initialize the content classifier
      • Train the content classifiers
    • Generative AI classification
      • Generative AI classification description examples
      • Activate project-wide generative AI classification
      • Enable AI classification for a class
    • Configure classification thresholds
    • Instruction classifier
      • Manage classification instructions
      • Combine several phrases in an instruction
      • Export classification instructions
      • Import classification instructions
      • Import classification instructions using Import as New
    • Subtree classifiers
      • Enable subtree classification for a class
      • Add a subtree classifier
      • Modify a subtree classifier
      • Delete a subtree classifier
    • Classification rules and hierarchical evaluation
      • Classification based on extraction
      • Configure classification redirection
      • Subtree classification hierarchical rule
      • Single child wins over parent
      • Parent represents competing children
      • Local not-flag
      • Propagated not-flag
      • Confident and unconfident classification results
      • Reclassification of documents via script
    • Evaluate multi-page classification
    • Redirect the classification result
    • View classification results
    • Classification benchmarks
      • Generate classification benchmark for all classification settings
      • Generate a classification benchmark for a specific classifier
      • View classification benchmark statistics
      • Save classification benchmark results
      • Optimize classification results using the Selection document set
      • Compare Classification Benchmark results
        • Compare two classification benchmark files
        • Change the classification benchmark baseline
      • Add classification benchmark exceptions
    • Update a project after document type changes in Advanced Studio
  • Set up document separation
    • What type of document separation to use
    • Document separation and the classification training set
    • Classification settings and their effect on document separation
    • Trainable document separation
      • Configure trainable document separation
      • Import an old Project Planner TDS model
      • How pages are classified for trainable document separation
    • Standard document separation
      • How to handle unclassified pages with standard document separation
      • Configure standard document separation
    • Train document separation
    • Test document separation
    • Separation benchmarks
      • Generate a separation benchmark
      • View and filter separation benchmark results
  • Set up online learning
    • Enable online learning
    • Advanced online learning options
    • Separation and classification online learning
      • Configure separation and classification online learning
      • Separation and classification training documents
      • Dynamic online learning for separation and classification
      • Document separation and classification New Samples and the project life cycle
      • Import document separation and classification online learning documents
      • Mark documents for document separation & classification online learning via script
    • Extraction online learning
      • Configure extraction online learning
      • Extraction New Samples and the project life cycle
      • Dynamic knowledge bases
      • Knowledge bases
      • Trainable locator methods
        • What locator to use
        • Specific training of trainable locators
        • Layout ID and extraction online learning
        • Vendor name and ID recognition
      • Best practices for extraction training
      • Extraction online learning and training documents
      • Automatically flag documents for extraction online learning
      • Scripts and extraction online learning
      • Train your project for extraction
      • Conflict management
        • Resolve conflicts
        • Resolve training conflicts
        • Best practices for conflict resolution
      • Edit training documents
        • Train table fields
        • Assign a single value
        • Assign split values
        • Edit keywords
        • Field navigation
        • Document validation
      • Importance of value coordinates
  • Set up extraction
    • Extraction sequence
    • Locator extraction types
    • Extraction methods
    • Locator method types
    • Evaluator method types
    • Trainable locator method types
      • Trainable locator inheritance
    • Inheritance
      • Locator extraction types and inheritance
      • Locator inheritance
        • Copy an inherited locator
        • Override an inherited locator
      • Field group inheritance
      • Field inheritance
        • Edit the formatting for an inherited field
        • Interrupt the inheritance relationship for a field
        • Multiple selection to edit inherited fields
        • Restore the inheritance relationship for a field
        • Fields and locators with interrupted inheritance
    • Locator alternatives
    • Manage locators
      • Locator order
      • Open locator properties
      • Work with locators
      • Rearrange locator order in a class
      • Automatic field creation and assignment
        • Navigate between locators and fields
      • Assign a locator to a field
      • Configure regions
      • Locator knowledge bases
        • Configure the Knowledge Base tab
        • Protect knowledge bases
        • Manage knowledge base activation codes
      • Test locators
        • Dependent locator tests
        • Change the test execution mode
    • Manage field groups
      • Upgrades and field groups
      • Work with field groups
      • Rearrange the field group order in a class
      • Move fields between field groups
    • Manage fields
      • Project-level fields
      • Class-level fields
      • Simple fields
        • Configure simple field details
      • Table fields
        • Configure table field details
      • Work with fields
      • Rearrange the field order in a field group
      • Assign a field to a locator
      • Bulk edit multiple selected fields
      • Field confidences
      • Field formatting
      • Fixed value
    • Extraction benchmarks
      • View extraction results
      • Perform an extraction benchmark
      • Save an extraction benchmark
      • Extraction benchmark comparison
      • Export an extraction benchmark
    • Address Evaluator
      • Configure an Address Evaluator
    • Address Locator
      • Configure an Address Locator
      • Reduce address alternatives with regions
    • Advanced Evaluator
      • Add subfields to the Evaluator Subfields list
      • Create a custom subfield for evaluation
      • Subfields for evaluation
      • Evaluation steps
      • Define input locators for a subfield
      • Advanced Evaluator test results
    • Advanced Table Locator
      • Multiple tables with the same table label
      • Configure an Advanced Table Locator
      • Table training
    • Advanced Zone Locator
      • Advanced Zone Locator and registration
      • Manage the reference and sample documents
      • Zones and the Document Viewer (zone mode)
      • Advanced Zone Locator subfields
      • Manual zone recognition
        • Add a manual zone
        • Configure an existing zone
        • Create a local image cleanup profile
        • Add zones for a group of check boxes
        • Copy a zone for voting
        • Duplicate zones
        • Anchor zones
          • Manual anchoring
          • Anchor reference points
          • Suitable and unsuitable anchors
          • Text anchor zone recognition
          • Locator anchor zone recognition
          • Can intersect border
          • Anchor confidence
          • Add a manual anchor
          • Move or resize an anchor zone
          • Map a zone to an anchor
          • Map multiple zones to an anchor
          • Hide anchors and zones on a document
          • View corresponding zones and anchors
        • Add a subfield
          • Combine the results from multiple zones
          • Use the best result from multiple zone results
      • Automatic zone recognition with the Zone Wizard
        • Tips for optimal zone discovery
        • Zone Wizard and existing zones
        • Presets and automatic zone recognition
        • Add zones with the Zone Wizard
        • Zone selection in the Zone Wizard
      • Advanced Zone Locator field confidences
      • Hide anchors and zones on a document
      • Test zones on the reference document
    • AI Table Locator
      • Configure an AI Table Locator
    • Auto Extract Locator
      • Best practices for subfield descriptions
      • Inferred or derived fields
      • Description limitations
      • Configure an Auto Extract Locator
    • Bar Code Locator
      • Bar code types
      • Bar code orientation
      • Bar code confidence
      • Enhanced bar codes
      • Bar code voting
      • Configure a Bar Code Locator
      • Change the bar code type
      • Specify bar code length restrictions
    • Check Locator
      • Check Locator amounts
      • Test results for checks
      • Country-specific settings
        • Countries A - F
        • Countries I - U
        • Field usability detection based on country
        • Document types by country
      • Check endorsements
      • Configure a Check Locator
    • Classification Locator
      • Configure a Classification Locator
    • Database Evaluator
      • Configure a Database Evaluator
      • Map database fields to locator subfields
      • Specify the criteria needed to match a database record
      • Specify the data returned by the Database Evaluator
    • Database Locator
      • Exclusion database
        • Adjust exclusion database settings
      • Databases and the Database Locator
      • Database search masks
      • Configure a Database Locator
      • Add a database search mask
      • Delete a database search mask
    • Format Locator
      • Format definitions
      • Configure format definitions
      • Configure evaluation settings
      • Configure general settings
    • Invoice Header Locator
      • Configure Invoice Header Locator settings
      • Invoice Header Locator keywords
      • Add Invoice Header Locator keywords
    • Key-Value Pairs Locator
      • Enable key-value pair extraction
      • Key-value pair subfields
        • Add a subfield
        • Add subfield keywords
        • Add keyword dictionary to subfield
      • Key-value pairs and testing
      • Configure a Key-Value Pairs Locator
    • Line Item Matching Locator
      • The principles of price calculation
      • Input locators
      • Line items and match by script
      • Configure a Line Item Matching Locator
      • Test Line Item Matching Locator results
    • Named Entity Locator
      • Configure a Named Entity Locator
      • Entity extraction using a table
    • OCR Voting Evaluator
      • Configure an OCR Voting Evaluator
      • OCR Voting Evaluator and test results
    • Predefined Document Type Locator
      • Licensing and the Predefined Document Type Locator
      • Supported document types
      • Configure a Predefined Document Type Locator
      • Deactivate document type subfields
      • Assign table model and map table columns
      • Predefined Document Type Locator testing
    • Relation Evaluator
      • Configure a Relation Evaluator
    • Script Locator
      • Configure a Script Locator
    • Sentiment Locator
    • Standard Evaluator
      • Configure a Standard Evaluator
    • Summary Locator
      • Configure a Summary Locator
    • Table Locator
      • Automatic table extraction
      • Configure a Table Locator
      • Automatic registration in manual table mode
      • Optional rows and comments in manual table mode
      • Define table cells in manual table mode
      • Define a master item
      • Define model column mappings
      • Order numbers
      • Embedded columns
      • Test Table Locator results
      • Use expert mode for testing tables
    • Text Content Locator
      • Configure the Text Content Locator
      • Train the Text Content Locator
    • Themes Locator
      • Configure a Themes Locator
    • Trainable Evaluator
      • Configure a Trainable Evaluator
      • Train the Trainable Evaluator
    • Vendor Locator
      • Vendor Locator fields
      • Configure vendor locator general settings
      • Configure vendor locator purchase order behavior
      • Configure vendor locator banking details
    • Trainable Group Locator
      • Configure a Trainable Group Locator
    • Amount Group Locator
      • VAT-based locations
      • Configure an Amount Group Locator
    • Invoice Group Locator
      • Configure an Invoice Group Locator
    • Order Group Locator
      • Configure an Order Group Locator
    • Extraction change history
  • Set up Validation
    • Validation sequence
    • Validation methods
      • Work with validation methods
        • Add a standard validation method
        • Add a date validation method
        • Add a regular expression validation method
        • Add an invoice validation method
          • Invoice field validation and rounding mode
          • Invoice field validation and field reconstruction
          • Invoice field validation and discount rates
        • Add a single field script validation method
        • Add a multi-field script validation method
 › Use Transformation Designer › Project Settings general settings

Project Settings general settings

Use the General tab to configure commonly used features such as online learning, automatic rotation, and scripting.

This tab has the following settings groups:

  • Rotation

  • Monitoring

  • Color Conversion to Black and White

  • Online Learning

  • Scripting

Tungsten TotalAgility 2026.3
×