You are here: Start » AVL.NET » AVS.TrainOcr_SVM Method
AVS.TrainOcr_SVM Method
Trains an OCR support vector machines classifier.
Namespace: | AvlNet |
---|---|
Assembly: | AVL.NET.dll |
Syntax
public static void TrainOcr_SVM ( IList<AvlNet.CharacterSample> inCharacterSamples, AvlNet.Size inNormalizationSize, float inRegularizationConstant, float inStopEpsilon, bool inUseShrinkingHeuristics, AvlNet.CharacterFeatures inCharacterFeatures, 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). | ||
inRegularizationConstant | float | <0.0f, INF> | 1.0f | Preventing overfitting. Default value: 1.0f. | |
inStopEpsilon | float | 0.001f | Epsilon for stopping criterion. Default value: 0.001f. | ||
inUseShrinkingHeuristics | bool | True | Heuristics may speed up computations. Default value: True. | ||
inCharacterFeatures | AvlNet.CharacterFeatures | (Pixels: True) | Character features used to identify characters. Default value: (Pixels: True). | ||
outOcrModel | AvlNet.OcrModel | Trained OcrSvmModel used to recognize characters. | |||
outTrainingAccuracy | float | The overall training score. |
Function Overrides
- TrainOcr_SVM(IList<CharacterSample>, Size, Nullable<Single>, Nullable<Single>, Single, Single, Boolean, Nullable<Size>, Nullable<Int32>, CharacterFeatures, OcrModel, Single)
- TrainOcr_SVM(IList<CharacterSample>, Size, Nullable<Single>, Nullable<Single>, Single, Single, Boolean, Nullable<Size>, Nullable<Int32>, CharacterFeatures, OcrModel, Single, IList<Image>)