Back to Adaptive Vision Library website
You are here: Start » Function Reference » Optical Character Recognition » MakeCharacterSamples
MakeCharacterSamples
Creates training font samples from the provided regions.
Header: | AVL.h |
---|
Syntax
C++
C#
void avl::MakeCharacterSamples ( const atl::Array<avl::Region>& inCharacterRegions, const atl::String& inCharacters, atl::Array<avl::CharacterSample>& outCharacterSamples )
Parameters
Name | Type | Default | Description | |
---|---|---|---|---|
inCharacterRegions | const Array<Region>& | Array of character regions | ||
inCharacters | const String& | Character that should be assigned to corresponding regions | ||
outCharacterSamples | Array<CharacterSample>& | Array of CharacterSamples |
Description
The operation creates a set of character samples used to train OcrMlpModel in the TrainOcr_MLP filter. Consecutive letters in inCharacters correspond to consecutive regions in inCharacterRegions.
Remarks
The length of inCharacters must be equal to the size of the inCharacterRegions array.
To read more about how to use OCR technique, refer to Machine Vision Guide: Optical Character Recognition
Errors
Error type | Description |
---|---|
DomainError | At least a single character should be provided in MakeCharacterSamples. |
DomainError | The size of inCharacterRegions and the length of inCharacters are not equal in MakeCharacterSamples. |
DomainError | Parameter inCharacterRegions contains empty region in MakeCharacterSamples. |
See Also
- TrainOcr_MLP – Trains an OCR multilayer perceptron classifier.