You are here: Start » Function Reference » Computer Vision » Optical Character Recognition » ExtractText

ExtractText

Header:	FIL.h
Namespace:	fil
Module:	OCR

Ready-to-use tool for extracting and splitting character to single characters.

Syntax

void fil::ExtractText
(
	const fil::Image& inImage,
	const fil::Rectangle2D& inRoi,
	const fil::CoordinateSystem2D& inRoiAlignment,
	const fil::TextSegmentation& inSegmentationModel,
	ftl::Array<fil::Region>& outCharacters,
	fil::Region& diagTextRegion,
	ftl::Array<fil::Region>& diagAlignedCharacters,
	fil::Rectangle2D& diagAlignedRoi
)

Parameters

Name	Type	Description
inImage	const Image&	An input image with text
inRoi	const Rectangle2D&	Location of the text
inRoiAlignment	const CoordinateSystem2D&	Adjusts the region of interest to the position of the inspected object
inSegmentationModel	const TextSegmentation&	Model used for separating text from background
outCharacters	Array<Region>&	Split characters aligned to ROI
diagTextRegion	Region&	Region of text after extraction
diagAlignedCharacters	Array<Region>&	Character regions preserving original image orientation
diagAlignedRoi	Rectangle2D&	ROI rectangle after alignment

Description

This filter distinguish characters from the background using a set of algorithms. This filter performs two steps: text extraction and text segmentation:

Text extraction – in this step filter uses some basic thresholding methods to get a characters region from the image.
Text segmentation – split previously found region into separate regions contains character.

Input inRoi should contains only a single line of text.

Hints

If the object location is variable, pass an appropriate local coordinate system to inRoiAlignment.
Before defining inSegmentationModel first specify inRoi – the rectangle in which characters will be extracted.

Examples

Result of reading text using the ExtractText.

Remarks

To read more about how to use traditional OCR technique, refer to Machine Vision Guide: Optical Character Recognition - traditional method

Errors

List of possible exceptions:

Error type	Description
DomainError	Invalid segmentation algorithm in ExtractText.
DomainError	Invalid thresholding algorithm in ExtractText.