F_VN_ReferenceColorSimilarityExp_TcVnVector3_LREAL

F_VN_ReferenceColorSimilarityExp_TcVnVector3_LREAL 1:

Computes the similarity to a reference color for each pixel in the source image. (expert function)
Can use available TwinCAT Job Tasks for executing parallel code regions.
Can return partial results when canceled by Watchdog.

Syntax

Definition:

FUNCTION F_VN_ReferenceColorSimilarityExp_TcVnVector3_LREAL : HRESULT
VAR_INPUT
    ipSrcImage       : ITcVnImage;
    ipDestImage      : Reference To ITcVnImage;
END_VAR
VAR_IN_OUT
    aRefColor        : TcVnVector3_LREAL;
END_VAR
VAR_INPUT
    fVariance        : REAL;
    fLuminanceWeight : REAL;
    hrPrev           : HRESULT;
END_VAR

F_VN_ReferenceColorSimilarityExp_TcVnVector3_LREAL 2: Inputs

Name

Type

Description

ipSrcImage

ITcVnImage

RGB source image (USINT, 3 channels)

ipDestImage

Reference To ITcVnImage

Returns the similarity to aRefColor for each pixel in ipSrcImage (USINT, 1 channel. An appropriate destination image will be created if required.)

fVariance

REAL

Allowed color variance (0.1 - 0.3 might be a good start to try)

fLuminanceWeight

REAL

Weight the impact of the luminance ([0..1], e.g. set to 0 to be more resistant to unequal illumination, but might be required to differentiate between some colors)

hrPrev

HRESULT

HRESULT indicating the result of previous operations (If SUCCEEDED(hrPrev) equals false, no operation is executed.)

F_VN_ReferenceColorSimilarityExp_TcVnVector3_LREAL 3: In/Outputs

Name

Type

Description

aRefColor

TcVnVector3_LREAL

Reference color (RGB, [0..255])

F_VN_ReferenceColorSimilarityExp_TcVnVector3_LREAL 4: Return value

HRESULT

Further information

There are three ways to pass the reference color to the corresponding function:

To train a color model, a corresponding F_VN_TrainImageColor function must be used. The two color models differ only in the data type, functionally there are no differences. The ITcVnMlModel is the general data type for ML models for which there are also function blocks for loading and saving. Therefore, this data type and the corresponding functions should be used if the trained color model is to be saved to disk.

Samples

Required License

TC3 Vision Base

System Requirements

Development environment

Target platform

PLC libraries to include

TwinCAT V3.1.4024.54 or later

PC or CX (x64) with PL50, e.g. Intel 4-core Atom CPU

Tc3_Vision