Data Preprocessing

Manage and preprocess image data for deep learning

Preprocessing image data to ensure that it is in a format that the network can accept is a common first step in deep learning workflows. For example, you can resize image input to match the size of an image input layer. You can also preprocess data to enhance desired features or reduce artifacts that can bias the network. For example, you can normalize or remove noise from input data.

You can preprocess image input with operations such as resizing by using datastores and functions available in MATLAB^® and Deep Learning Toolbox™. Other MATLAB toolboxes offer functions, datastores, and apps for labeling, processing, and augmenting deep learning data. Use specialized tools from other MATLAB toolboxes to process data for domains such as image processing, object detection, and semantic segmentation.

Apps

Image Labeler	Label images for computer vision applications
Video Labeler	Label video for computer vision applications
Ground Truth Labeler	Label ground truth data for automated driving applications

Functions

`imageDatastore`	Datastore for image data
`augmentedImageDatastore`	Transform batches to augment image data
`imageDataAugmenter`	Configure image data augmentation
`augment`	Apply identical random transformations to multiple images
`minibatchqueue`	Create mini-batches for deep learning (Since R2020b)

Topics

Preprocess Images for Deep Learning
Learn how to resize images for training, prediction, and classification, and how to preprocess images using data augmentation, transformations, and specialized datastores.
Preprocess Volumes for Deep Learning
Read and preprocess volumetric image and label data for 3-D deep learning.
Datastores for Deep Learning
Learn how to use datastores in deep learning applications.
Optimize Datastores for Deep Learning Performance
Explore methods for speeding up deep learning workflows that use datastores.
Deep Learning in MATLAB
Discover deep learning capabilities in MATLAB using convolutional neural networks for classification and regression, including pretrained networks and transfer learning, and training on GPUs, CPUs, clusters, and clouds.
Deep Learning Tips and Tricks
Learn how to improve the accuracy of deep learning networks.
Data Sets for Deep Learning
Discover data sets for various deep learning tasks.

Featured Examples

Prepare Datastore for Image-to-Image Regression

Prepare a datastore for training an image-to-image regression network using the transform and combine functions of ImageDatastore.

Open Live Script

Augment Images for Deep Learning Workflows

Perform common kinds of randomized image augmentation such as geometric transformations, cropping, and adding noise.

Open Live Script

Create and Explore Datastore for Image Classification

Create, read, and augment an image datastore for use in training a deep learning network. In particular, this example shows how to create an ImageDatastore object from a collection of images, read and extract the properties of the datastore, and create an augmentedImageDatastore for use during training.

Open Live Script