show the confusion metrics as figure?

Dear All,

I was evaluate the segmentation result deep learning method as below.

>> %Evaluate the prediction results against the ground truth.
metrics = evaluateSemanticSegmentation(pxdsResults,pxdsTest);
%Display the properties of the semanticSegmentationMetrics object.
metrics
%Display the classification accuracy, the intersection over union, and the boundary F-1 score for each class. These values are stored in the ClassMetrics property.
metrics.ClassMetrics
%Display the normalized confusion matrix that is stored in the NormalizedConfusionMatrix property.
metrics.ConfusionMatrix
Evaluating semantic segmentation results
----------------------------------------
* Selected metrics: global accuracy, class accuracy, IoU, weighted IoU, BF score.
* Processed 1 images.
* Finalizing... Done.
    * Data set metrics:

GlobalAccuracy    MeanAccuracy    MeanIoU    WeightedIoU    MeanBFScore
______________    ____________    _______    ___________    ___________

0.99961          0.75114       0.74253      0.99923        0.9087   


metrics = 

semanticSegmentationMetrics with properties:

ConfusionMatrix: [2×2 table]
NormalizedConfusionMatrix: [2×2 table]
DataSetMetrics: [1×5 table]
ClassMetrics: [2×3 table]
ImageMetrics: [1×5 table]


ans =

2×3 table

Accuracy      IoU      MeanBFScore
________    _______    ___________

background    0.99997     0.99961      0.99867  
tumor         0.50231     0.48546      0.81873  


ans =

2×2 table

background    tumor
__________    _____

background    5.8938e+05      15 
tumor                215     217 

Anyone know how to show the confusion metrics as figure?

[Chunru]

doc confusionchart

[mohd akmal masud]

?

[Chunru]

???

Answer 1

[Mrutyunjaya Hiremath]

After Evaluating semantic segmentation results, add the below code:

% Get the confusion matrix from the 'metrics' object
confusion_matrix = table2array(metrics.ConfusionMatrix);

classLabels = categorical({'background','tumor'})

cm = confusionchart(confusion_matrix, classLabels,...
    'Title','Confusion Matrix',...
    'ColumnSummary','column-normalized', ...
    'RowSummary','row-normalized');

[mohd akmal masud]

Thank you sir. Its work!

[Mrutyunjaya Hiremath]

Most Welcome Sir.. :)