Deep learning segmentation

Object detection using pre-trained algorithms via ONNX models. The object detection algorithms supported can be found under the parameter model type.

See ONNX image segmentation for more information.

TIP

In the analyze tree add the descriptor Segmentation label and select a text file including the names of objects in the ONNX file.

Parameters

Model type

The .onnx model type. Available options are:

Faster R-CNN
YOLO v4
YOLO v5

Onnx file

Select the pre-trained ONNX file for the selected model type.

Source

On which image the ONNX segmentation should be applied. The pseudo-rgb image or a painted prediction image.

Confidence

The confidence level required by the model for an object to be categorized.

Normalize the pixel values

Only applicable to Faster-RCNN

If Normalize and center is used the values will be scaled to 0-1 before the is subtracted and the used in the division. See below.

No normalization

Normalize and center

Image dimension order

Only applicable to Faster-RCNN

In which order the input dimensions are:

Width / Height
Height / Width

Output layer to use

Only applicable to YOLOv5

Which type of output layer to use:

Sigmoid layer
Detection layer

Min area

The minimum number of pixels for an object to be included.

Max area

The maximum number of pixels for an object to be included.

If 0 no maximum area is defined.

Object filter

Use an expression to further exclude unwanted objects based on shape.

Standard arithmetic (+,-,/,* …) and comparison operators (=,>,< …) as well as some mathematical expressions (…) and constant values () can be used in expressions.

Expand to see all available operator

Arithmetic Operator	Description
`-`	Subtract
`+`	Add
`/`	Divide
`*`	Multiply
`%`	Modulo
`^`	Raised to a power

Comparison Operator	Description
`=`	Equal to
`\|` `OR`	TRUE if any of the conditions separated by OR is TRUE
`&` `AND`	TRUE if all the conditions separated by AND is TRUE
`!=` `<>`	Not equal to
`<`	Less than
`<=`	Less than or equal to
`>`	Greater than
`>=`	Greater than or equal to

Function operator	Description
`SQRT(N)`
`SIN(N)`
`COS(N)`
`EXP(N)`
`LOG(N)`
`LOG10(N)`
`AVG(N)`
`ROUND(N)`

Constants	Description
`TRUE`	Always evaluates to TRUE
`FALSE`	Always evaluates to FALSE
`INF`	token value
`PI`	approximated to

Properties that can be used for the Expression:

Area
Length
Width
Circumference
Regularity
Roundness
Angle
D1
D2
X
Y
MaxBorderDistance
BoundingBoxArea

For details on each available property see: Object properties Details

Shrink

Takes away x numbers of pixels at the borders of the objects included in images.

Separate

Normal
- Can have both separated and combined objects.
Separate adjacent objects
- All objects are defined separately.
Merge all objects into one
- All objects are defined as one.
Merge all objects per row
- All objects per row segmentation are defined as one.
Merge all objects per column
- All objects per column segmentation are defined as one.

Max objects

Max number of objects in image, takes the first objects sorted by confidence.

Inverse

✅ Includes the opposite of the sample specified in the Deep learning image model.

⬜ Includes the sample specified from the Deep learning image model.

Link

Only visible when applicable

Link output objects from two or more segmentations to top segmentation. Descriptors can then be added to the common object output and will be calculated for objects from all segmentations.

Descriptors after object will be calculated for all three segmentations (Sample1, Sample2 and Sample3)

The segmentations must be at same level to be available for linking.