You are here: Start » Function Reference » Optical Character Recognition Deprecated » RecognizeCharacters_SVM_Deprecated

RecognizeCharacters_SVM_Deprecated

Classifies input regions into characters. Based on the Support Vector Machines model.

Syntax

void avl::RecognizeCharacters_SVM_Deprecated
(
	const atl::Array<avl::Region>& inCharacterRegions,
	const avl::OcrSvmModel& inOcrModel,
	atl::Optional<const avl::Size&> inCharacterSize,
	const bool inDotPrint,
	const avl::CharacterSortingOrder::Type inCharacterSorting,
	atl::Optional<float> inMinScore,
	atl::Optional<int> inMinSpaceWidth,
	atl::String& outCharacters,
	atl::Array<float>& outScores,
	atl::Array<atl::Array<avl::OcrCandidate>>& outCandidates,
	atl::Array<avl::Image>& diagNormalizedCharacters,
	atl::Array<avl::Box>& diagCharactersBoxes
)

void RecognizeCharacters_SVM_Deprecated
(
	Region[] inCharacterRegions,
	OcrSvmModel inOcrModel,
	Size? inCharacterSize,
	bool inDotPrint,
	CharacterSortingOrder inCharacterSorting,
	float? inMinScore,
	int? inMinSpaceWidth,
	out System.String outCharacters,
	out float[] outScores,
	out OcrCandidate[][] outCandidates,
	out Image[] diagNormalizedCharacters,
	out Box[] diagCharactersBoxes
)

Parameters

Name	Type	Range	Default	Description
inCharacterRegions	const Array<Region>&			Array of character regions to recognize
inOcrModel	const OcrSvmModel&			Trained OcrSvmModel used to recognize characters
inCharacterSize	Optional<const Size&>		NIL	Size of single monospaced character if needed
inDotPrint	const bool			Dot-printed characters preprocessing
inCharacterSorting	const CharacterSortingOrder::Type		LeftToRight	Sorting order of input characters
inMinScore	Optional<float>	0.0 - 1.0	NIL	Minimal value of accepted result. Otherwise char '*' will be placed.
inMinSpaceWidth	Optional<int>	0 -	NIL	Minimal distance between characters where space character will be inserted
outCharacters	String&			Result of characters recognition
outScores	Array<float>&			Classification result score
outCandidates	Array<Array<OcrCandidate>>&			Array of a character classification results and their score
diagNormalizedCharacters	Array<Image>&			Images of normalized characters used in character recognition
diagCharactersBoxes	Array<Box>&			Bounding boxes of characters

Description

The operation recognizes characters from given regions using prepared OcrSvmModel.

This operation requires trained SVM classifier provided in the inOcrModel input. For further details about creating and learning fonts please refer to the documentation of filters InitOcr_SVM_Deprecated and TrainOcr_SVM_Deprecated.

Filter requires regions specified in the inCharacterRegions. Each of the input region must contain single character. To separate characters in the region use SplitRegionIntoExactlyNCharacters or SplitRegionIntoMultipleCharacters.

The inCharacterSorting parameter defines the sorting order of the input characters provided in inCharacterRegions.

The parameter inDotPrint turns on the dedicated smoothing for characters printed using jet printer in dot-matrix form.

The parameter inCharacterSize defines size of monospaced (fixed-width) font. If the parameter is set to auto character will be recognized as proportional font. For further information about font types please refer to the documentation of filter TrainOcr_SVM.

The input inMinSpaceWidth value indicates minimal distance between characters where space character will be inserted to result string. When the value is marked as auto no spaces will be inserted.

The output outCharacters contains recognized characters. The recognition score of each recognized character is stored in the outScores.

Remarks

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

Errors