Semantic Segmentation

Semantic image segmentation

Semantic segmentation associates each pixel of an image with a class label, such as flower, person, road, sky, or car. Use the Image Labeler and the Video Labeler apps to interactively label pixels and export the label data for training a neural network.


Image LabelerLabel images for computer vision applications
Video LabelerLabel video for computer vision applications


expand all

semanticsegSemantic image segmentation using deep learning
semanticSegmentationMetricsSemantic segmentation quality metrics
evaluateSemanticSegmentationEvaluate semantic segmentation data set against ground truth
labeloverlayOverlay label matrix regions on 2-D image
countEachLabelCount occurrence of pixel label for data source images
pixelLabelTrainingDataCreate training data for semantic segmentation from ground truth
pixelLabelDatastoreDatastore for pixel label data
pixelLabelImageDatastoreDatastore for semantic segmentation networks
crop2dLayerNeural network layer in a neural network that can be used to crop an input feature map
fcnLayersCreate fully convolutional network layers for semantic segmentation
pixelClassificationLayerCreate pixel classification layer for semantic segmentation
segnetLayersCreate SegNet layers for semantic segmentation
unetLayersCreate U-Net layers for semantic segmentation


Semantic Segmentation Basics

Segment objects by class using deep learning

Label Pixels for Semantic Segmentation

Label pixels for semantic segmentation using Image Labeler, Video Labeler, or Ground Truth Labeler app.

R-CNN, Fast R-CNN, and Faster R-CNN Basics

R-CNN, Fast R-CNN, and Faster R-CNN basics

Datastores for Deep Learning (Deep Learning Toolbox)

Learn how to use datastores in deep learning applications.

Featured Examples