You are here: Start » Function Reference » Computer Vision » Deep Learning » MergeCharactersIntoLines

MergeCharactersIntoLines

Header:	FIL.h
Namespace:	fil
Module:	DL_OCR

Converts a output of DL_ReadCharacters to lines of text.

Syntax

void fil::MergeCharactersIntoLines
(
	const ftl::Array<fil::OcrResult>& inCharacters,
	float inMaxGap,
	float inMaxShift,
	float inMargin,
	int inMinLength,
	bool inFlatten,
	ftl::Array<fil::Rectangle2D >& outLines,
	ftl::Array <ftl::String >& outStrings,
	ftl::Array< ftl::Conditional<int> >& outMapping
)

Parameters

Name	Type	Range	Default	Description
inCharacters	const Array<OcrResult>&			Output of DL_ReadCharacters
inMaxGap	float	0.0 - 10.0	0.25f	Maximum horizontal gap between joint characters' boxes, denoted as % of 'A' char height
inMaxShift	float	0.0 - 1.0	0.25f	Maximum vertical misalignment between joint character's boxes, denoted as % of 'A' char height
inMargin	float	0.0 - 10.0		Additional margin added to result, denoted as % of 'A' char height
inMinLength	int	1 - 200	1	Minimal number of chars to create line
inFlatten	bool		False	If True, it concatenates the words on the line into a single result string, otherwise each word is a separate result string
outLines	Array<Rectangle2D >&			Minimal Box which cover all selected character boxes
outStrings	Array <String >&			Text of merged characters
outMapping	Array< Conditional<int> >&			Mapping between input characters and output lines, outMapping[i] stores the index line to which inCharacters[i] belongs. If outMapping[i] is NIL it means that inCharacters[i] has not been added to any line