Class: Google::Cloud::DocumentAI::V1::OcrConfig

Inherits:

Object

Object
Google::Cloud::DocumentAI::V1::OcrConfig

show all

Extended by:: Protobuf::MessageExts::ClassMethods

Includes:: Protobuf::MessageExts

Defined in:: proto_docs/google/cloud/documentai/v1/document_io.rb

Overview

Config for Document OCR.

Defined Under Namespace

Classes: Hints, PremiumFeatures

Instance Attribute Summary collapse

#advanced_ocr_options ⇒ ::Array<::String>
A list of advanced OCR options to further fine-tune OCR behavior.
#compute_style_info ⇒ ::Boolean deprecated Deprecated.
This field is deprecated and may be removed in the next major version update.
#disable_character_boxes_detection ⇒ ::Boolean
Turn off character box detector in OCR engine.
#enable_image_quality_scores ⇒ ::Boolean
Enables intelligent document quality scores after OCR.
#enable_native_pdf_parsing ⇒ ::Boolean
Enables special handling for PDFs with existing text information.
#enable_symbol ⇒ ::Boolean
Includes symbol level OCR information if set to true.
#hints ⇒ ::Google::Cloud::DocumentAI::V1::OcrConfig::Hints
Hints for the OCR model.
#premium_features ⇒ ::Google::Cloud::DocumentAI::V1::OcrConfig::PremiumFeatures
Configurations for premium OCR features.

Instance Attribute Details

#advanced_ocr_options ⇒ `::Array<::String>`

# File 'proto_docs/google/cloud/documentai/v1/document_io.rb', line 168

class OcrConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Hints for OCR Engine
  # @!attribute [rw] language_hints
  #   @return [::Array<::String>]
  #     List of BCP-47 language codes to use for OCR. In most cases, not
  #     specifying it yields the best results since it enables automatic language
  #     detection. For languages based on the Latin alphabet, setting hints is
  #     not needed. In rare cases, when the language of the text in the
  #     image is known, setting a hint will help get better results (although it
  #     will be a significant hindrance if the hint is wrong).
  class Hints
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configurations for premium OCR features.
  # @!attribute [rw] enable_selection_mark_detection
  #   @return [::Boolean]
  #     Turn on selection mark detector in OCR engine. Only available in OCR 2.0
  #     (and later) processors.
  # @!attribute [rw] compute_style_info
  #   @return [::Boolean]
  #     Turn on font identification model and return font style information.
  # @!attribute [rw] enable_math_ocr
  #   @return [::Boolean]
  #     Turn on the model that can extract LaTeX math formulas.
  class PremiumFeatures
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#compute_style_info ⇒ `::Boolean`

Deprecated.

This field is deprecated and may be removed in the next major version update.

Returns Turn on font identification model and return font style information. Deprecated, use PremiumFeatures.compute_style_info instead.

# File 'proto_docs/google/cloud/documentai/v1/document_io.rb', line 168

class OcrConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Hints for OCR Engine
  # @!attribute [rw] language_hints
  #   @return [::Array<::String>]
  #     List of BCP-47 language codes to use for OCR. In most cases, not
  #     specifying it yields the best results since it enables automatic language
  #     detection. For languages based on the Latin alphabet, setting hints is
  #     not needed. In rare cases, when the language of the text in the
  #     image is known, setting a hint will help get better results (although it
  #     will be a significant hindrance if the hint is wrong).
  class Hints
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configurations for premium OCR features.
  # @!attribute [rw] enable_selection_mark_detection
  #   @return [::Boolean]
  #     Turn on selection mark detector in OCR engine. Only available in OCR 2.0
  #     (and later) processors.
  # @!attribute [rw] compute_style_info
  #   @return [::Boolean]
  #     Turn on font identification model and return font style information.
  # @!attribute [rw] enable_math_ocr
  #   @return [::Boolean]
  #     Turn on the model that can extract LaTeX math formulas.
  class PremiumFeatures
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#disable_character_boxes_detection ⇒ `::Boolean`

# File 'proto_docs/google/cloud/documentai/v1/document_io.rb', line 168

class OcrConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Hints for OCR Engine
  # @!attribute [rw] language_hints
  #   @return [::Array<::String>]
  #     List of BCP-47 language codes to use for OCR. In most cases, not
  #     specifying it yields the best results since it enables automatic language
  #     detection. For languages based on the Latin alphabet, setting hints is
  #     not needed. In rare cases, when the language of the text in the
  #     image is known, setting a hint will help get better results (although it
  #     will be a significant hindrance if the hint is wrong).
  class Hints
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configurations for premium OCR features.
  # @!attribute [rw] enable_selection_mark_detection
  #   @return [::Boolean]
  #     Turn on selection mark detector in OCR engine. Only available in OCR 2.0
  #     (and later) processors.
  # @!attribute [rw] compute_style_info
  #   @return [::Boolean]
  #     Turn on font identification model and return font style information.
  # @!attribute [rw] enable_math_ocr
  #   @return [::Boolean]
  #     Turn on the model that can extract LaTeX math formulas.
  class PremiumFeatures
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#enable_image_quality_scores ⇒ `::Boolean`

# File 'proto_docs/google/cloud/documentai/v1/document_io.rb', line 168

class OcrConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Hints for OCR Engine
  # @!attribute [rw] language_hints
  #   @return [::Array<::String>]
  #     List of BCP-47 language codes to use for OCR. In most cases, not
  #     specifying it yields the best results since it enables automatic language
  #     detection. For languages based on the Latin alphabet, setting hints is
  #     not needed. In rare cases, when the language of the text in the
  #     image is known, setting a hint will help get better results (although it
  #     will be a significant hindrance if the hint is wrong).
  class Hints
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configurations for premium OCR features.
  # @!attribute [rw] enable_selection_mark_detection
  #   @return [::Boolean]
  #     Turn on selection mark detector in OCR engine. Only available in OCR 2.0
  #     (and later) processors.
  # @!attribute [rw] compute_style_info
  #   @return [::Boolean]
  #     Turn on font identification model and return font style information.
  # @!attribute [rw] enable_math_ocr
  #   @return [::Boolean]
  #     Turn on the model that can extract LaTeX math formulas.
  class PremiumFeatures
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#enable_native_pdf_parsing ⇒ `::Boolean`

# File 'proto_docs/google/cloud/documentai/v1/document_io.rb', line 168

class OcrConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Hints for OCR Engine
  # @!attribute [rw] language_hints
  #   @return [::Array<::String>]
  #     List of BCP-47 language codes to use for OCR. In most cases, not
  #     specifying it yields the best results since it enables automatic language
  #     detection. For languages based on the Latin alphabet, setting hints is
  #     not needed. In rare cases, when the language of the text in the
  #     image is known, setting a hint will help get better results (although it
  #     will be a significant hindrance if the hint is wrong).
  class Hints
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configurations for premium OCR features.
  # @!attribute [rw] enable_selection_mark_detection
  #   @return [::Boolean]
  #     Turn on selection mark detector in OCR engine. Only available in OCR 2.0
  #     (and later) processors.
  # @!attribute [rw] compute_style_info
  #   @return [::Boolean]
  #     Turn on font identification model and return font style information.
  # @!attribute [rw] enable_math_ocr
  #   @return [::Boolean]
  #     Turn on the model that can extract LaTeX math formulas.
  class PremiumFeatures
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#enable_symbol ⇒ `::Boolean`

# File 'proto_docs/google/cloud/documentai/v1/document_io.rb', line 168

class OcrConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Hints for OCR Engine
  # @!attribute [rw] language_hints
  #   @return [::Array<::String>]
  #     List of BCP-47 language codes to use for OCR. In most cases, not
  #     specifying it yields the best results since it enables automatic language
  #     detection. For languages based on the Latin alphabet, setting hints is
  #     not needed. In rare cases, when the language of the text in the
  #     image is known, setting a hint will help get better results (although it
  #     will be a significant hindrance if the hint is wrong).
  class Hints
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configurations for premium OCR features.
  # @!attribute [rw] enable_selection_mark_detection
  #   @return [::Boolean]
  #     Turn on selection mark detector in OCR engine. Only available in OCR 2.0
  #     (and later) processors.
  # @!attribute [rw] compute_style_info
  #   @return [::Boolean]
  #     Turn on font identification model and return font style information.
  # @!attribute [rw] enable_math_ocr
  #   @return [::Boolean]
  #     Turn on the model that can extract LaTeX math formulas.
  class PremiumFeatures
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#hints ⇒ `::Google::Cloud::DocumentAI::V1::OcrConfig::Hints`

# File 'proto_docs/google/cloud/documentai/v1/document_io.rb', line 168

class OcrConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Hints for OCR Engine
  # @!attribute [rw] language_hints
  #   @return [::Array<::String>]
  #     List of BCP-47 language codes to use for OCR. In most cases, not
  #     specifying it yields the best results since it enables automatic language
  #     detection. For languages based on the Latin alphabet, setting hints is
  #     not needed. In rare cases, when the language of the text in the
  #     image is known, setting a hint will help get better results (although it
  #     will be a significant hindrance if the hint is wrong).
  class Hints
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configurations for premium OCR features.
  # @!attribute [rw] enable_selection_mark_detection
  #   @return [::Boolean]
  #     Turn on selection mark detector in OCR engine. Only available in OCR 2.0
  #     (and later) processors.
  # @!attribute [rw] compute_style_info
  #   @return [::Boolean]
  #     Turn on font identification model and return font style information.
  # @!attribute [rw] enable_math_ocr
  #   @return [::Boolean]
  #     Turn on the model that can extract LaTeX math formulas.
  class PremiumFeatures
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#premium_features ⇒ `::Google::Cloud::DocumentAI::V1::OcrConfig::PremiumFeatures`

# File 'proto_docs/google/cloud/documentai/v1/document_io.rb', line 168

class OcrConfig
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Hints for OCR Engine
  # @!attribute [rw] language_hints
  #   @return [::Array<::String>]
  #     List of BCP-47 language codes to use for OCR. In most cases, not
  #     specifying it yields the best results since it enables automatic language
  #     detection. For languages based on the Latin alphabet, setting hints is
  #     not needed. In rare cases, when the language of the text in the
  #     image is known, setting a hint will help get better results (although it
  #     will be a significant hindrance if the hint is wrong).
  class Hints
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Configurations for premium OCR features.
  # @!attribute [rw] enable_selection_mark_detection
  #   @return [::Boolean]
  #     Turn on selection mark detector in OCR engine. Only available in OCR 2.0
  #     (and later) processors.
  # @!attribute [rw] compute_style_info
  #   @return [::Boolean]
  #     Turn on font identification model and return font style information.
  # @!attribute [rw] enable_math_ocr
  #   @return [::Boolean]
  #     Turn on the model that can extract LaTeX math formulas.
  class PremiumFeatures
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

Class: Google::Cloud::DocumentAI::V1::OcrConfig

Overview

Defined Under Namespace

Instance Attribute Summary collapse

Instance Attribute Details

#advanced_ocr_options ⇒ ::Array<::String>

#compute_style_info ⇒ ::Boolean

#disable_character_boxes_detection ⇒ ::Boolean

#enable_image_quality_scores ⇒ ::Boolean

#enable_native_pdf_parsing ⇒ ::Boolean

#enable_symbol ⇒ ::Boolean

#hints ⇒ ::Google::Cloud::DocumentAI::V1::OcrConfig::Hints

#premium_features ⇒ ::Google::Cloud::DocumentAI::V1::OcrConfig::PremiumFeatures