evalPerformanceClassifier: A function for calculating performance metrics for...

In joaofgoncalves/SegOptim: Optimization of Image Segmentation Parameters for Object-Based Image Analysis (OBIA)

A function for calculating performance metrics for SOptim.Classifier objects

Description

This function can be used to calculate all available performance evaluation metrics both for single- or multi-class problems using a SOptim.Classifier objects (check out calibrateClassifier for more details).

Usage

evalPerformanceClassifier(obj)

Arguments

obj	An object of class SOptim.Classifier generated by calibrateClassifier with option runFullCalibration = TRUE.

Details

List of available evaluation metrics: — SINGLE-CLASS —

• Kappa - Cohen Kappa (maximum)

• PSS - Peirce Skill score (maximum)

• GSS - Gerrity Skill score (maximum)

• AUC - Area Under the Receiver Operating Curve

— MULTI-CLASS —

• Kappa - Cohen Kappa

• PSS - Peirce Skill score

• GSS - Gerrity Skill score

• Accuracy - Overall accuracy

Value

A numeric matrix with the evaluation metrics. For single-class problems an additional column by metric (with suffix "_Thresh") is added to the matrix with threshold values used to maximize each evaluation metric.

joaofgoncalves/SegOptim documentation built on Feb. 5, 2024, 11:10 p.m.