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 Labeler | Label images for computer vision applications |
Video Labeler | Label video for computer vision applications |
semanticseg | Semantic image segmentation using deep learning |
segnetLayers | Create SegNet layers for semantic segmentation |
unetLayers | Create U-Net layers for semantic segmentation |
fcnLayers | Create fully convolutional network layers for semantic segmentation |
pixelLabelDatastore | Datastore for pixel label data |
pixelLabelImageDatastore | Datastore for semantic segmentation networks |
pixelLabelTrainingData | Create training data for semantic segmentation from ground truth |
pixelClassificationLayer | Create pixel classification layer for semantic segmentation |
crop2dLayer | Neural network layer in a neural network that can be used to crop an input feature map |
semanticSegmentationMetrics | Semantic segmentation quality metrics |
evaluateSemanticSegmentation | Evaluate semantic segmentation data set against ground truth |
labeloverlay | Overlay label matrix regions on 2-D image |
countEachLabel | Count occurrence of pixel label for data source images |
Segment objects by class using deep learning
R-CNN, Fast R-CNN, and Faster R-CNN Basics
R-CNN, Fast R-CNN, and Faster R-CNN basics