Document

96 public types in this namespace, organized by kind.

Models & Types (52)

Type Summary
ABINet<T> ABINet (Autonomous, Bidirectional, Iterative Network) for text recognition.
AlternativeAnswer<T> Represents an alternative answer with lower confidence.
CharacterRecognition<T> Represents a single recognized character with its confidence.
CheckboxResult<T> Result of checkbox detection.
Dessurt<T> Dessurt (Document End-to-end Self-Supervised Understanding and RecogniTion) for document understanding.
DiT<T> DiT (Document Image Transformer) for document image understanding.
DocBank<T> DocBank model for document page segmentation and layout analysis.
DocFormer<T> DocFormer neural network for end-to-end document understanding.
DocGCN<T> DocGCN (Document Graph Convolutional Network) for document understanding using graph neural networks.
DocOwl<T> DocOwl (mPLUG-DocOwl) for document understanding with multimodal large language model.
DocumentClassificationResult<T> Result of document classification.
DocumentLayoutResult<T> Represents the result of document layout detection.
DocumentQAResult<T> Represents the result of document question answering.
DocumentRegion<T> Represents a detected document region.
Donut<T> Donut (Document Understanding Transformer) - OCR-free end-to-end document understanding model.
EvidenceRegion<T> Represents a region in the document that provides evidence for an answer.
ExtractedEntity<T> An extracted entity from a document.
FormFieldResult<T> Result of form field extraction.
FormField<T> Represents an extracted form field.
InfographicVQA<T> InfographicVQA for visual question answering on infographics.
KeyInfoExtractionResult<T> Result of key information extraction.
LayoutGraph<T> LayoutGraph: graph-based document layout analysis after GLAM (Wang et al.
LayoutLM<T> LayoutLM (v1) neural network for document understanding with layout-aware pre-training.
LayoutLMv2<T> LayoutLMv2 neural network for document understanding with visual features.
LayoutLMv3<T> LayoutLMv3 neural network for document understanding with unified text and image pre-training.
LayoutRegion<T> Represents a single detected layout region in a document.
LayoutXLM<T> LayoutXLM neural network for multilingual document understanding.
LiLT<T> LiLT (Language-Independent Layout Transformer) for document understanding.
MATCHA<T> MATCHA (Math-Aware Transformer for Chart Harvesting and Analysis) for chart understanding.
Nougat<T> Nougat neural network for academic document understanding.
OCRBlock<T> Represents a block (paragraph or region) of recognized text.
OCRLine<T> Represents a line of recognized text.
OCRResult<T> Represents the result of OCR (Optical Character Recognition) processing.
OCRWord<T> Represents a single recognized word.
OrderedElement<T> Represents an element with reading order information.
PICK<T> PICK (Processing Key Information extraction) for document key information extraction.
PSENetLoss<T> PSENet’s training objective (Wang et al.
PSENet<T> PSENet (Progressive Scale Expansion Network) for text detection.
PageSegmentationResult<T> Represents the result of page segmentation.
Pix2Struct<T> Pix2Struct neural network for screenshot to structured output conversion.
ReadingOrderResult<T> Result of reading order detection.
SVTR<T> SVTR (Scene Text Visual Transformer) for text recognition.
SignatureResult<T> Result of signature detection.
TRIE<T> TRIE (Text Reading and Information Extraction) for end-to-end document understanding.
TableCell<T> Represents a single cell in a table.
TableRegion<T> Represents a detected table region in a document.
TableStructureResult<T> Represents the result of table structure recognition.
TableTransformer<T> TableTransformer for table detection and structure recognition using DETR-style architecture.
TextDetectionResult<T> Represents the result of text detection in an image.
TextRecognitionResult<T> Represents the result of text recognition from a cropped image.
TextRegion<T> Represents a detected text region in an image.
UDOP<T> UDOP (Unifying Vision, Text, and Layout for Universal Document Processing) neural network.

Base Classes (1)

Type Summary
DocumentNeuralNetworkBase<T> Base class for document-focused neural networks that can operate in both ONNX inference and native training modes.

Interfaces (11)

Type Summary
IDocumentClassifier<T> Interface for document classification models.
IDocumentModel<T> Base interface for all document AI models in AiDotNet.
IDocumentQA<T> Interface for document question answering models.
IFormUnderstanding<T> Interface for form understanding models that extract structured fields from documents.
ILayoutDetector<T> Interface for document layout detection models.
IOCRModel<T> Interface for OCR (Optical Character Recognition) models.
IPageSegmenter<T> Interface for page segmentation models that identify different regions in document pages.
IReadingOrderDetector<T> Interface for reading order detection models.
ITableExtractor<T> Interface for table detection and structure recognition models.
ITextDetector<T> Interface for text detection models that locate text regions in images.
ITextRecognizer<T> Interface for text recognition models that read text from cropped image regions.

Enums (7)

Type Summary
ConfidenceLevel Confidence levels for document AI predictions.
DiTModelSize The DiT variants released with the paper (Li et al.
DocumentRegionType Types of document regions that can be detected by page segmentation.
DocumentType Types of documents supported by document AI models.
FormFieldType Types of form fields that can be detected.
LayoutElementType Types of layout elements that can be detected in documents.
TableExportFormat Export formats for extracted table data.

Options & Configuration (25)

Type Summary
ABINetOptions Configuration options for the ABINet document model.
DessurtOptions Configuration options for the Dessurt document model.
DiTOptions Configuration options for the DiT document model.
DocBankOptions Configuration options for the DocBank document model.
DocFormerOptions Configuration options for the DocFormer document model.
DocGCNOptions Configuration options for the DocGCN document model.
DocOwlOptions Configuration options for the DocOwl document model.
DocumentModelOptions<T> Base configuration options for all document AI models.
DonutOptions Configuration options for the Donut document model.
InfographicVQAOptions Configuration options for the InfographicVQA document model.
LayoutGraphOptions Configuration options for the LayoutGraph document model.
LayoutLMOptions Configuration options for the LayoutLM document model.
LayoutLMv2Options Configuration options for the LayoutLMv2 document model.
LayoutLMv3Options Configuration options for the LayoutLMv3 document model.
LayoutXLMOptions Configuration options for the LayoutXLM document model.
LiLTOptions Configuration options for the LiLT document model.
MATCHAOptions Configuration options for the MATCHA document model.
NougatOptions Configuration options for the Nougat document model.
PICKOptions Configuration options for the PICK document model (Yu et al., ICPR 2020).
PSENetOptions Configuration options for the PSENet document model.
Pix2StructOptions Configuration options for the Pix2Struct document model.
SVTROptions Configuration options for the SVTR document model.
TRIEOptions Configuration options for the TRIE document model.
TableTransformerOptions Configuration options for the TableTransformer document model.
UDOPOptions Configuration options for the UDOP document model.