Need better scanning performance?

Get a FREE customized reading template.

LocalizationModes

Determines how to localize text lines. It consists of one or more modes, each mode representing a different localization process.

Remarks

Introduced in Dynamsoft Capture Vision version 3.2.1000.

JSON Structure

Location in template:

LabelRecognizerTaskSettingOptions[i]
    └── SectionArray[j] (Section object)
        └── StageArray[k] (Stage object where Stage = "SST_LOCALIZE_TEXT_LINES")
            └── LocalizationModes

Parent object: LocalizeTextLinesStage

Example:

"LocalizationModes":
[
    {
        "Mode": "LM_NEURAL_NETWORK",
        "ModelNameArray": ["MRZLocalization"]
    },
    {
        "Mode": "LM_GENERAL"
    }
]

This snippet shows only the LocalizationModes parameter.

To use it, embed this parameter within a LocalizeTextLinesStage object.

For the complete JSON structure, see:

Full JSON Structure

Minimal Valid JSON

Parameter Details

Parameter LocalizationModes consist of a group of localization mode objects. Each localization mode object includes a candidate mode and a series of auxiliary mode arguments. The structure of the localization mode object is shown as follow:

Mode Arguments

Mode Argument Name	Mode Argument Summary
Mode (Required)	Description Any one in Candidate Mode List as string
	Type String
	Candidate Mode List LM_NEURAL_NETWORK LM_GENERAL
ModelNameArray (Optional)	Description Sets the names of a text localization model.
	Type String Array
	Range Each element is the name of a model. Candidate values: "MRZLocalization".
	Default Value null
	Valid For LM_NEURAL_NETWORK.
	Remarks When set to null, model "MRZLocalization" will be used by default.

Default Settings

If the LocalizationModes is not configured in your template file, the following settings will be used as the default settings.

{
    "LocalizationModes":
    [
        {
            "Mode": "LM_GENERAL"
        }
    ]
}

Candidate Modes Descriptions

LM_GENERAL

Localizes text lines using general image processing algorithms.

LM_NEURAL_NETWORK

Localizes text lines by utilizing a neural network model. This mode has the following arguments for further cuztomization.

Available Mode Arguments:

ModelNameArray