You are here: Start » AVL.NET » AVS.TrainOcr_MLP Method
AVS.TrainOcr_MLP Method
Trains an OCR multilayer perceptron classifier.
Namespace: | AvlNet |
---|---|
Assembly: | AVL.NET.dll |
Syntax
public static void TrainOcr_MLP ( IList<AvlNet.CharacterSample> inCharacterSamples, AvlNet.Size inNormalizationSize, AvlNet.CharacterFeatures inCharacterFeatures, float inLearningRate, float inMomentum, int inIterationCount, AvlNet.OcrModel outOcrModel, out float outTrainingAccuracy )
Parameters
Name | Type | Range | Default | Description | |
---|---|---|---|---|---|
inCharacterSamples | System.Collections.Generic.IList<AvlNet.CharacterSample> | Training font created from sample regions. | |||
inNormalizationSize | AvlNet.Size | (Width: 16, Height: 16) | The character size after normalization. Default value: (Width: 16, Height: 16). | ||
inCharacterFeatures | AvlNet.CharacterFeatures | (Pixels: True) | Character features used to distinguish characters from each other. Default value: (Pixels: True). | ||
inLearningRate | float | <0.01f, 1.0f> | 0.6f | Suppression level of changes during learning process. Default value: 0.6f. | |
inMomentum | float | <0.0f, 1.0f> | 0.75f | Value of classifier learning momentum. Default value: 0.75f. | |
inIterationCount | int | <1, +INF> | 100 | Learning iteration count. Default value: 100. | |
outOcrModel | AvlNet.OcrModel | Trained OcrMlpModel used to recognize characters. | |||
outTrainingAccuracy | float | The overall training score. |
Function Overrides
- TrainOcr_MLP(IList<CharacterSample>, Size, NullableRef<IList<Int32>>, Nullable<Int32>, CharacterFeatures, Single, Single, Int32, Nullable<Size>, OcrModel, Single)
- TrainOcr_MLP(IList<CharacterSample>, Size, NullableRef<IList<Int32>>, Nullable<Int32>, CharacterFeatures, Single, Single, Int32, Nullable<Size>, OcrModel, Single, Profile, IList<Image>)