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.
|Combine data from multiple datastores|
|Count occurrence of pixel or box labels|
|Ground truth label data|
|Datastore for image data|
|Datastore for semantic segmentation networks|
|Datastore for pixel label data|
|Create training data for semantic segmentation from ground truth|
|Balance pixel labels by oversampling block locations in big images|
|Apply geometric transformation to image|
|Create randomized 2-D affine transformation|
|Create rectangular center cropping window|
|Create randomized rectangular cropping window|
|Create DeepLab v3+ convolutional neural network for semantic image segmentation|
|Create pixel classification layer using generalized Dice loss for semantic segmentation|
|Create fully convolutional network layers for semantic segmentation|
|Create pixel classification layer for semantic segmentation|
|Create SegNet layers for semantic segmentation|
|Create U-Net layers for semantic segmentation|
|Create 3-D U-Net layers for semantic segmentation of volumetric images|
|Evaluate semantic segmentation data set against ground truth|
|Contour matching score for image segmentation|
|Sørensen-Dice similarity coefficient for image segmentation|
|Jaccard similarity coefficient for image segmentation|
|Semantic segmentation quality metrics|
Label pixels for training a semantic segmentation network by using a labeling app.
Learn how the labeling apps store pixel label data.
Segment objects by class using deep learning
Understand how to use point clouds for deep learning.
Datastores for Deep Learning (Deep Learning Toolbox)
Learn how to use datastores in deep learning applications.
Create training data for object detection or semantic segmentation using the Image Labeler or Video Labeler.