You are here: Start » DLInvoke.DL_ReadCharacters_Multiple
Performs optical character recognition using a pretrained deep learning model on multiple regions of interest.
| Namespace: | Avl |
|---|---|
| Assembly: | AvlNet.DL.Cpu.dll |
Syntax
C++
C#
public static void DL_ReadCharacters_Multiple ( Avl.Image inImage, List<Avl.Rectangle2D> inMultiRoi, Optional<Avl.CoordinateSystem2D> inRoiAlignment, Avl.ReadCharactersModelId inModelId, List<int> inCharHeights, float inWidthScale, float inCharSpacing, Optional<string> inCharRange, float inMinScore, float inMinQuality, Avl.Polarity inPolarization, float inContrastThreshold, bool inCalculateCandidates, bool inRemoveBoundaryCharacters, Optional<int> inCanvasWidth, Optional<int> inCanvasHeight, List<List<Avl.OcrResult>> outCharacters, List<List<List<Avl.OcrCandidate>>> outCandidates, List<List<Avl.Region>> outMasks, List<Avl.Rectangle2D> outAlignedRois, Diagnostic<List<Avl.Image>> diagCanvas )
Parameters
| Name | Type | Range | Default | Description | |
|---|---|---|---|---|---|
![]() | inImage | Avl.Image | Input image. | ||
![]() | inMultiRoi | System.Collections.Generic.List<Avl.Rectangle2D> | Limits the areas where recognized characters are located. | ||
![]() | inRoiAlignment | Atl.Optional<Avl.CoordinateSystem2D> | |||
![]() | inModelId | Avl.ReadCharactersModelId | Identifier of a Read Characters model. Default value: (). | ||
![]() | inCharHeights | System.Collections.Generic.List<int> | Average height of characters in pixels for each ROI. Default value: {35}. | ||
![]() | inWidthScale | float | Scales image width by the given factor. Default value: 1.0f. | ||
![]() | inCharSpacing | float | Distance between characters denoted as fraction of inCharHeight. Default value: 0.0f. | ||
![]() | inCharRange | Atl.Optional<string> | Limits the set of wanted characters. Default value: "A-Z,a-z,0-9,\\\\,/,-". | ||
![]() | inMinScore | float | Sets a minimum required score for a character to be returned. Default value: 0.5f. | ||
![]() | inMinQuality | float | Specifies the minimum quality threshold a character must meet to be returned. Default value: 0.0f. | ||
![]() | inPolarization | Avl.Polarity | Sets a required polarity for a character to be returned. Default value: Any. | ||
![]() | inContrastThreshold | float | Sets a threshold for a contrast of found characters. Default value: 0.0f. | ||
![]() | inCalculateCandidates | bool | If set to true then outCandidates is calculated. Default value: True. | ||
![]() | inRemoveBoundaryCharacters | bool | If set to true characters that are not entirely contained in the ROI are filtered out. Default value: False. | ||
![]() | inCanvasWidth | Atl.Optional<int> | Maximum width of internal canvas buffer. If not set, dynamic size mode is used, used only on CUDA execution. Default value: 8192. | ||
![]() | inCanvasHeight | Atl.Optional<int> | Maximum height of internal canvas buffer. If not set, dynamic size mode is used, used only on CUDA execution. Default value: 64. | ||
![]() | outCharacters | System.Collections.Generic.List<System.Collections.Generic.List<Avl.OcrResult>> | |||
![]() | outCandidates | System.Collections.Generic.List<System.Collections.Generic.List<System.Collections.Generic.List<Avl.OcrCandidate>>> | Array of the most likely characters. The first element is the character from outCharacters. | ||
![]() | outMasks | System.Collections.Generic.List<System.Collections.Generic.List<Avl.Region>> | Masks of found characters (in Extended model). Contains empty regions in case of using model not supporting masks (in Fast and Balanced model). | ||
![]() | outAlignedRois | System.Collections.Generic.List<Avl.Rectangle2D> | Input rois after transformation. | ||
![]() | diagCanvas | Avl.Diagnostic<System.Collections.Generic.List<Avl.Image>> | Internal canvas images used for OCR. |



