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.

Apps

Image Labeler	Label images for computer vision applications
Video Labeler	Label video for computer vision applications

Functions

expand all

Load Training Data

`combine`	Combine data from multiple datastores
`countEachLabel`	Count occurrence of pixel or box labels
`groundTruth`	Ground truth label data
`imageDatastore`	Datastore for image data
`pixelLabelImageDatastore`	Datastore for semantic segmentation networks
`pixelLabelDatastore`	Datastore for pixel label data
`pixelLabelTrainingData`	Create training data for semantic segmentation from ground truth

Augment and Preprocess Training Data

`balancePixelLabels`	Balance pixel labels by oversampling block locations in big images
`imwarp`	Apply geometric transformation to image
`imcrop`	Crop image
`imresize`	Resize image
`transform`	Transform datastore
`randomAffine2d`	Create randomized 2-D affine transformation
`centerCropWindow2d`	Create rectangular center cropping window
`randomCropWindow2d`	Create randomized rectangular cropping window

Design Semantic Segmentation Deep Learning Networks

`deeplabv3plusLayers`	Create DeepLab v3+ convolutional neural network for semantic image segmentation
`dicePixelClassificationLayer`	Create pixel classification layer using generalized Dice loss for semantic segmentation
`fcnLayers`	Create fully convolutional network layers for semantic segmentation
`pixelClassificationLayer`	Create pixel classification layer for semantic segmentation
`segnetLayers`	Create SegNet layers for semantic segmentation
`unetLayers`	Create U-Net layers for semantic segmentation
`unet3dLayers`	Create 3-D U-Net layers for semantic segmentation of volumetric images
`focalCrossEntropy`	Compute focal cross-entropy loss

Segment Images Using Deep Learning

semanticseg Semantic image segmentation using deep learning

Visualize Segmentation

`labeloverlay`	Overlay label matrix regions on 2-D image
`labelvolshow`	Display labeled volume
`insertObjectMask`	Insert masks in image or video stream

Evaluate Segmentation Results

`evaluateSemanticSegmentation`	Evaluate semantic segmentation data set against ground truth
`bfscore`	Contour matching score for image segmentation
`dice`	Sørensen-Dice similarity coefficient for image segmentation
`jaccard`	Jaccard similarity coefficient for image segmentation
`segmentationConfusionMatrix`	Confusion matrix of multi-class pixel-level image segmentation
`semanticSegmentationMetrics`	Semantic segmentation quality metrics

Topics

Get Started

Label Pixels for Semantic Segmentation

Label pixels for training a semantic segmentation network by using a labeling app.

How Labeler Apps Store Exported Pixel Labels

Learn how the labeling apps store pixel label data.

Choose Function to Visualize Detected Objects

Compare visualization functions.

Getting Started with Semantic Segmentation Using Deep Learning

Segment objects by class using deep learning

Getting Started with Point Clouds Using Deep Learning

Understand how to use point clouds for deep learning.

Create Training Data for Semantic Segmentation

Datastores for Deep Learning (Deep Learning Toolbox)

Learn how to use datastores in deep learning applications.

Training Data for Object Detection and Semantic Segmentation

Create training data for object detection or semantic segmentation using the Image Labeler or Video Labeler.

Featured Examples

Semantic Segmentation Using Dilated Convolutions

Semantic Segmentation Using Dilated Convolutions.

Open Live Script

Semantic Segmentation of Multispectral Images Using Deep Learning

Train a U-Net convolutional neural network to perform semantic segmentation of a multispectral image with seven channels: three color channels, three near-infrared channels, and a mask.

Open Live Script

3-D Brain Tumor Segmentation Using Deep Learning

Train a 3-D U-Net neural network and perform semantic segmentation of brain tumors from 3-D medical images. The example shows how to train a 3-D U-Net network and also provides a pretrained network. Use of a CUDA-capable NVIDIA™ GPU with compute capability 3.0 or higher is highly recommended for 3-D semantic segmentation (requires Parallel Computing Toolbox™).

Open Live Script