IPageSegmenter<T>

Interfaces · AiDotNet.Document.Interfaces

Interface for page segmentation models that identify different regions in document pages.

Implements: IDocumentModel<T>

Known implementations: DocBank<T>

For Beginners

When you look at a document page, you can easily identify different sections - titles, paragraphs, images, tables. Page segmentation teaches computers to do the same thing, labeling each region with its type.

Example usage:

How It Works

Page segmentation models divide a document page into semantic regions like text blocks, figures, tables, headers, footers, and captions.

Properties

Property Summary
IReadOnlyList<DocumentRegionType> SupportedRegionTypes { get; } Gets the region types this segmenter can detect.
bool SupportsInstanceSegmentation { get; } Gets whether this segmenter performs instance segmentation (separate instances of same type).

Methods

Method Summary
PageSegmentationResult<T> SegmentPage(Tensor<T> documentImage) Segments a document page into semantic regions.
PageSegmentationResult<T> SegmentPage(Tensor<T> documentImage, double confidenceThreshold) Segments a document page with a custom confidence threshold.
Tensor<T> GetSegmentationMask(Tensor<T> documentImage) Gets the pixel-level segmentation mask.