FisFilter_DL_DetectAnomalies1

Header:	FIL.h
Namespace:	fil
Module:	DL_DA

Executes a Detect Anomalies 1 model on a single input image.

Syntax

void fil::FisFilter_DL_DetectAnomalies1
(
	const fil::Image& inImage,
	const fil::DetectAnomalies1ModelId& inModelId,
	const bool inReconstruct,
	const float inScoreScale,
	fil::Heatmap& outHeatmap,
	bool& outIsValid,
	float& outScore,
	bool& outIsConfident,
	float& outT1,
	float& outT2,
	ftl::Optional<fil::Image&> outReconstructedImage = ftl::NIL
)

Parameters

Name	Type	Range	Default	Description
inImage	const Image&			Input image
inModelId	const DetectAnomalies1ModelId&			Identifier of a Detect Anomalies 1 model
inReconstruct	const bool		True	Enables computing a reconstructed image, which may extend execution time
inScoreScale	const float	0.5 - 1.5	1.0f	Scale factor for T1 and T2 (default value results in usage of T1 and T2 from model)
outHeatmap	Heatmap&			Returns a heatmap indicating found anomalies
outIsValid	bool&			Returns true if no anomalies were found
outScore	float&			Returns score of the image
outIsConfident	bool&			Returns false if the score is between T1 and T2 (inclusive)
outT1	float&			Returns T1 'Good' threshold value
outT2	float&			Returns T2 'Bad' threshold value
outReconstructedImage	Optional<Image&>		NIL	Returns the reconstructed image

Requirements

For input inImage only pixel formats are supported: 1⨯uint8, 3⨯uint8.

Read more about pixel formats in Image documentation.

Optional Outputs

The computation of following outputs can be switched off by passing value ftl::NIL to these parameters: outReconstructedImage.

Hints

It is recommended that the deep learning model is deployed with DL_DetectAnomalies1_Deploy first and connected through the inModelId input.
If one decides not to use DL_DetectAnomalies1_Deploy, then the model will be loaded in the first iteration. It will take up to several seconds.

Remarks

This filter should not be executed along with running Deep Learning Service as it may result in degraded performance or even out-of-memory errors.

Errors

List of possible exceptions:

Error type	Description
DomainError	Not supported inImage pixel format in FisFilter_DL_DetectAnomalies1. Supported formats: 1xUInt8, 3xUInt8.