Classes
class	oevislib_net.ComputerVision.OCR.MLP.Model
	Model using Artificial Neural Networks. More...

Functions
static MLP.Model	oevislib_net.ComputerVision.OCR.OCR.Train (Array< CharacterSample > inCharacterSamples, Size inNormalizationSize=null, Optional< Size > inCharacterSize=null, Optional< Array< int > > inHiddenLayerSizes=null, Array< CharacterFeaturesType > inCharacterFeatures=null, float inLearningRate=0.1f, float inMomentum=0.1f, int inIterationCount=100, Optional< float > outTrainingAccuracy=null, Optional< Array< Image > > outNormalizedCharacters=null)
	Trains a Multi-Layer Perceptron classifier.

Detailed Description

Function Documentation

MLP.Model oevislib_net.ComputerVision.OCR.OCR.Train	(	Array< CharacterSample >	inCharacterSamples,
		Size	inNormalizationSize = null,
		Optional< Size >	inCharacterSize = null,
		Optional< Array< int > >	inHiddenLayerSizes = null,
		Array< CharacterFeaturesType >	inCharacterFeatures = null,
		float	inLearningRate = 0::1f,
		float	inMomentum = 0::1f,
		int	inIterationCount = 100,
		Optional< float >	outTrainingAccuracy = null,
		Optional< Array< Image > >	outNormalizedCharacters = null )

inlinestatic

Trains a Multi-Layer Perceptron classifier.

Parameters

inCharacterSamples	Character samples used for training the model. Characters specified as labels will be interpreted as UTF-16 characters.
inNormalizationSize	Character size after normalization.
inCharacterSize	Size of the internal font.
inHiddenLayerSizes	Number of neurons in each layer (excluding the input and output layers).
inCharacterFeatures	Character features selected.
inLearningRate	Strength of the weight gradient term. Range: [0.01, 1].
inMomentum	Strength of the momentum term (the difference between weights on the 2 previous iterations). It provides some inertia to smooth the random fluctuations of the weights. Range: [0, 1].
inIterationCount	Maximum number of iterations. Range: [1, +inf).
outTrainingAccuracy	Training accuracy.
outNormalizedCharacters	Images of the normalized characters.