Load a pretrained network that performs binary segmentation of triangles against a background.

load('triangleSegmentationNetwork');

The三角形图data set has 100 test images with ground truth labels. Define the location of the data set.

dataSetDir = fullfile(toolboxdir('vision'),'visiondata',“三角形图”);

得到一个测试图像。

testImage = imread(fullfile(dataSetDir,“证词”,'image_001.jpg'）;

Get the corresponding ground truth label. The label image is stored as a numeric image, so convert the ground truth label to a categorical image.

gtLabel = imread(fullfile(dataSetDir,'testLabels','labeled_image_001.png'）;classNames = ["triangle","background"];labelids = [255 0];gtlabel =分类（gtlabel，labelids，classNames）;

Display the ground truth labels over the test image.

imshow(labeloverlay(testImage,gtLabel))

Perform semantic image segmentation.

predLabel = semanticseg(testImage,net);

Get the confusion matrix of the predicted labels and ground truth labels. The confusion matrix shows the segmentation correctly classified 21 pixels as triangle and 939 pixels as background. The confusion matrix also shows that the segmentation misclassified 64 background pixels as triangle. No triangle pixels are misclassified as background.

confusionMatrix = segmentationConfusionMatrix(predLabel,gtLabel)

confusionMatrix =2×221 0 64 939

要检查混淆矩阵的准确性，请在测试图像上显示预测标签。覆盖层与混淆矩阵中的值一致。

imshow(labeloverlay(testImage,predLabel))