IOCRModel<T>

Interfaces · AiDotNet.Document.Interfaces

Interface for OCR (Optical Character Recognition) models.

Implements: IDocumentModel<T>

Known implementations: Donut<T>

For Beginners

OCR is like teaching a computer to read. Given an image of text, the model outputs the actual text content and where each word/character is located.

Example usage:

How It Works

OCR models convert images containing text into machine-readable text strings, along with position information for each text element.

Properties

Property Summary
IReadOnlyList<string> SupportedLanguages { get; } Gets the languages supported by this OCR model.
bool IsOCRFree { get; } Gets whether this is an OCR-free model (end-to-end pixel-to-text).

Methods

Method Summary
OCRResult<T> RecognizeText(Tensor<T> documentImage) Performs full OCR on a document image.
OCRResult<T> RecognizeTextInRegion(Tensor<T> documentImage, Vector<T> region) Performs OCR on a specific region of the document.