Slug: aws-textract-model-v2 Version: 1.0.0 Infer: Yes

​

Overview

​

AWS Textract V2 Model

The AWS Textract V2 model is an enhanced version of the original Textract model, with improved bounding box calculations that better align with document coordinates. It uses Amazon’s advanced OCR and machine learning to extract text, forms, and tables from documents with greater precision.

​

Improvements in V2

• Enhanced Bounding Boxes: Revised calculations for more accurate text positioning
• Better Document Alignment: Improved spatial mapping to document coordinates
• Refined Text Positioning: More precise positioning of text elements
• Improved Line Recognition: Better identification of text line boundaries

​

How It Works

1. The model uploads your document to Amazon Web Services Textract
2. Textract analyzes the document using specialized machine learning algorithms
3. V2 applies improved coordinate transformations to the extraction results
4. The model processes the results, including:
   • Detected text with enhanced positioning information
   • Form fields with key-value pairs
   • Table structures with row and column data
5. Results are converted into a rich Kodexa document structure with accurate spatial information

​

Options Configuration

Option	Description
ignore_dash_lines	When enabled, removes dash-only lines from the extracted document structure
apply_skew	When enabled, corrects for document skew in the text positioning calculations

​

Process Flow

​

Extraction Capabilities

AWS Textract V2 excels at extracting:

• Text Content: Words, lines, and paragraphs with improved positioning
• Form Fields: Automatically identifies key-value pairs in forms
• Tables: Detects tabular structures with row and column relationships
• Handwriting: Identifies and extracts handwritten text
• Document Layout: Preserves the visual structure of the document with higher fidelity

​

Use Cases

This model is particularly useful for:

• High-Precision Layout Analysis: Applications requiring accurate text positioning
• Forms Processing: Extracting data from invoices, applications, and forms
• Table Extraction: Converting tabular information into structured data
• Document Digitization: Converting paper or image-based documents to digital formats
• Content Indexing: Making document content searchable and analyzable
• Form Field Automation: Identifying key-value pairs for automated data entry

​

When to Use V2 vs. V1

Choose Textract V2 when:

• You need more accurate bounding boxes
• Your application requires precise text positioning
• You’re working with complex document layouts
• You’re building layout-dependent applications
• You need better alignment between document coordinates and extracted text

---

​

Inference Options

The following options can be configured when using this model for inference:

Name	Label	Type	Description	Default	Required
ignore_dash_lines	Ignore Dash Line	boolean	Ignore the dash line in the document	False	No
apply_skew	Apply Skew	boolean	Apply skew correction to the document	True	No

---

​

Model Details

• Provider: Amazon Web Services