Back to Adaptive Vision Studio website
You are here: Start » Filter Reference » Deep Learning » DeepLearning_DetectAnomalies_Deprecated
Detects anomalies using trained deep-learning model.
Name | Type | Description | |
---|---|---|---|
inImage | Image | Input image | |
inRoi | Region* | Area of interest | |
inDeepModel | String | Trained model | |
outHeatmap | Image | Image contains heatmaps for each input image channel | |
outIsValid | Bool | Returns true if anomaly was not found | |
outScore | Real | Score of classification | |
outIsConfident | Bool | Returns "false" if score is between T1 and T2 | |
outReconstructedImage | Image | Returns network answer |
Requirements
For input inImage only pixel formats are supported: 1⨯uint8, 3⨯uint8.
Read more about pixel formats in Image documentation.
Errors
This filter can throw an exception to report error. Read how to deal with errors in Error Handling.
List of possible exceptions:
Error type | Description |
---|---|
DomainError | Empty image in DeepLearning_DetectAnomalies_Deprecated. |
DomainError | Empty ROI region in DeepLearning_DetectAnomalies_Deprecated |
DomainError | Invalid DeepModel in DeepLearning_DetectAnomalies_Deprecated. |
DomainError | Region's frame does not reflect image size |
Complexity Level
This filter is available on Basic Complexity Level.
Disabled in Lite Edition
This filter is disabled in Lite Edition. It is available only in full, Adaptive Vision Studio Professional version.