Classify (G Dataflow)

Region of interest specifying the location of the sample in the image.

The ROI must be one or more closed contours. If ROI descriptor is empty or not connected, the entire image is considered to be the region. For best performance, use only one rectangle or one rotated rectangle per sample.

Global Rectangle

Coordinates of the bounding rectangle.

Contours

Individual shapes that define an ROI.

ID

Object specifying if contour is the external or internal edge of an ROI.

Type

Shape type of the contour.

Coordinates

Relative position of the contour.

Reference to the classifier session on which the node operates.

Reference to the source image.

Error conditions that occur before this node runs.

The node responds to this input according to standard error behavior.

Standard Error Behavior

Many nodes provide an error in input and an error out output so that the node can respond to and communicate errors that occur while code is running. The value of error in specifies whether an error occurred before the node runs. Most nodes respond to values of error in in a standard, predictable way.

error in does not contain an error	error in contains an error
If no error occurred before the node runs, the node begins execution normally. If no error occurs while the node runs, it returns no error. If an error does occur while the node runs, it returns that error information as error out.	If an error occurred before the node runs, the node does not execute. Instead, it returns the error in value as error out.

Default: No error

Reference to the classifier session the node creates.

Reference to the source image.

Class into which the classifier session categorizes the input sample.

Array with one element for every class in the classifier session.

class

One of the classes in classifier session in.

distance

Distance from the closest sample in class to the input sample when performing nearest neighbor and k-nearest neighbor classification.

distance is the distance between the input sample and the center of each class when performing minimum mean distance classification.

Error information.

The node produces this output according to standard error behavior.

Standard Error Behavior

Many nodes provide an error in input and an error out output so that the node can respond to and communicate errors that occur while code is running. The value of error in specifies whether an error occurred before the node runs. Most nodes respond to values of error in in a standard, predictable way.

error in does not contain an error	error in contains an error
If no error occurred before the node runs, the node begins execution normally. If no error occurs while the node runs, it returns no error. If an error does occur while the node runs, it returns that error information as error out.	If an error occurred before the node runs, the node does not execute. Instead, it returns the error in value as error out.

Estimations of how well the classifier session classified the input.

The score can vary from 0 to 1000, where 1000 represents the best possible score.

classification score

Score that indicates how much better the assigned class represents the input sample than other classes represent the input.

identification score

Score that indicates the similarity of the input and the assigned class.

Use identification score only when you cannot reach a decision about the class of a sample using classification score alone.