Need better scanning performance?

Get a FREE customized reading template.

CaptureVisionModel Parameters

The CaptureVisionModel object defines how the library finds Convolutional Neural Networks (CNN) model files that support barcode decoding, character recognition and text line recognition.

Supported CNN Model Files

The following model files are currently supported.

• Code128Decoder.data
• Code39ITFDecoder.data
• DataMatrixQRCodeDeblur.data
• DataMatrixQRCodeLocalization.data
• EAN13Decoder.data
• LetterCharRecognition.data
• LowercaseCharRecognition.data
• MRZCharRecognition.data
• MRZLocalization.data
• MRZTextLineRecognition.data
• NumberCharRecognition.data
• NumberLetterCharRecognition.data
• NumberLowercaseCharRecognition.data
• NumberUppercaseCharRecognition.data
• OneDDeblur.data
• OneDLocalization.data
• PDF417Deblur.data
• PDF417Localization.data
• TextLineOrientationCls.data
• UppercaseCharRecognition.data
• VINCharRecognition.data

Example JSON

{
    "CaptureVisionModelOptions": [
        {
            "Name": "NumberLetterCharRecognition",
            "DirectoryPath": "D:\\CaptureVisionModel\\",
            "MaxModelInstances": 1,
            "ModelArgs": {
                "CharSet": {
                    "AddSpecialChars": ["-", ":"],
                    "ExcludeChars": ["O", "Q"]
                }
            }
        }
    ]
}

Hierarchical Structure

This tree shows one CaptureVisionModel object inside CaptureVisionModelOptions.

CaptureVisionModel
├── Name
├── DirectoryPath
├── MaxModelInstances
└── ModelArgs
  └── CharSet
    ├── AddSpecialChars
    └── ExcludeChars

Top-Level Parameters

Name

The name of the CaptureVisionModel object. It will be used as a unique identifier for the model.

DirectoryPath

The directory path of the model file.

MaxModelInstances

The maximum number of instances of the model.

ModelArgs

Sets advanced arguments of the model.

Nested Parameter Quick Links

Actual Nested Parameters in the Tree