You are here: Start » FIL.NET » FIS.TrainOcr_MLP Method
FIS.TrainOcr_MLP Method
Trains an OCR multilayer perceptron classifier.
Namespace: | FilNet |
---|---|
Assembly: | FIL.NET.dll |
Syntax
public static void TrainOcr_MLP ( IList<FilNet.CharacterSample> inCharacterSamples, FilNet.Size inNormalizationSize, NullableRef<IList<int>> inHiddenLayerSizes, int? inRandomSeed, FilNet.CharacterFeatures inCharacterFeatures, float inLearningRate, float inMomentum, int inIterationCount, FilNet.Size? inCharacterSize, FilNet.OcrModel outOcrModel, out float outTrainingAccuracy, FilNet.Profile diagError, IList<FilNet.Image> diagNormalizedCharacters )
Parameters
Name | Type | Range | Default | Description | |
---|---|---|---|---|---|
![]() | inCharacterSamples | System.Collections.Generic.IList<FilNet.CharacterSample> | Training font created from sample regions. | ||
![]() | inNormalizationSize | FilNet.Size | (Width: 16, Height: 16) | The character size after normalization. Default value: (Width: 16, Height: 16). | |
![]() | inHiddenLayerSizes | FilNet.NullableRef<System.Collections.Generic.IList<int>> | Internal structure of neuron layers used in classifier. Default value: ftl::NIL. | ||
![]() | inRandomSeed | int? | <0, +INF> | Random seed used by MLP classifier. Default value: ftl::NIL. | |
![]() | inCharacterFeatures | FilNet.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. |
![]() | inCharacterSize | FilNet.Size? | Size of fixed width font. Default value: ftl::NIL. | ||
![]() | outOcrModel | FilNet.OcrModel | Trained OcrMlpModel used to recognize characters. | ||
![]() | outTrainingAccuracy | float | The overall training score. | ||
![]() | diagError | FilNet.Profile | Changes of mean error level progress during learning process. | ||
![]() | diagNormalizedCharacters | System.Collections.Generic.IList<FilNet.Image> | Images of normalized characters used to train classifier. |
Function Overrides
- TrainOcr_MLP(IList<CharacterSample>, Size, CharacterFeatures, Single, Single, Int32, OcrModel, Single)
- TrainOcr_MLP(IList<CharacterSample>, Size, NullableRef<IList<Int32>>, Nullable<Int32>, CharacterFeatures, Single, Single, Int32, Nullable<Size>, OcrModel, Single)