Semantic image segmentation
Load Training Data
|Combine data from multiple datastores (Da R2019a)|
|Count occurrence of pixel or box labels|
|Ground truth label data|
|Datastore for image data|
|Datastore for pixel label data|
|Create training data for semantic segmentation from ground truth|
Augment and Preprocess Training Data
|Balance pixel labels by oversampling block locations in large images (Da R2020a)|
|Apply geometric transformation to image|
|Transform datastore (Da R2019a)|
|Create randomized 2-D affine transformation (Da R2019b)|
|Randomly select rectangular region in image (Da R2021a)|
|Create rectangular center cropping window (Da R2019b)|
Design Semantic Segmentation Deep Learning Networks
|Create DeepLab v3+ convolutional neural network for semantic image segmentation (Da R2019b)|
|Create pixel classification layer using generalized Dice loss for semantic segmentation (Da R2019b)|
|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 (Da R2019b)|
|Compute focal cross-entropy loss (Da R2020b)|
Segment Images Using Deep Learning
Evaluate Segmentation Results
|Evaluate semantic segmentation data set against ground truth|
|Contour matching score for image segmentation|
|Sørensen-Dice similarity coefficient for image segmentation|
|Generalized Sørensen-Dice similarity coefficient for image segmentation (Da R2021a)|
|Jaccard similarity coefficient for image segmentation|
|Confusion matrix of multi-class pixel-level image segmentation (Da R2020b)|
|Semantic segmentation quality metrics|
- 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 Mask R-CNN for Instance Segmentation
Perform multiclass instance segmentation using Mask R-CNN and deep learning.
- 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.
- Get Started with Image Preprocessing and Augmentation for Deep Learning
Preprocess data for deep learning applications with deterministic operations such as resizing, or augment training data with randomized operations such as random cropping.