Deep Learning for Image Processing
Deep learning uses neural networks to learn useful representations of features directly from data. For example, you can use a pretrained neural network to identify and remove artifacts like noise from images.
Create Datastores for Image Preprocessing
|Transform batches to augment image data|
|Datastore for use with blocks from |
|Denoising image datastore|
|Datastore for image data|
|Datastore for extracting random 2-D or 3-D random patches from images or pixel label images|
|Combine data from multiple datastores|
|Randomly alter color of pixels|
|Randomly select rectangular region in image|
|Create randomized cuboidal cropping window|
|Create rectangular center cropping window|
|Create cuboidal center cropping window|
|Spatial extents of 2-D rectangular region|
|Spatial extents of 3-D cuboidal region|
|Create randomized 2-D affine transformation|
|Create randomized 3-D affine transformation|
|Create output view for warping images|
|Remove image pixels within rectangular region of interest|
Resize and Reshape Deep Learning Input
|2-D resize layer|
|3-D resize layer|
|Resize spatial dimensions of |
|Depth to space layer|
|Space to depth layer|
|Rearrange spatial blocks of |
Create Deep Learning Networks
|Create encoder-decoder network|
|Create network with repeating block structure|
|Create encoder network from pretrained network|
|Create CycleGAN generator network for image-to-image translation|
|Create PatchGAN discriminator network|
|Create pix2pixHD global generator network|
|Add local enhancer network to pix2pixHD generator network|
|Create unsupervised image-to-image translation (UNIT) generator network|
|Perform inference using unsupervised image-to-image translation (UNIT) network|
Preprocess Image Data for Deep Learning
- Get Started with Image Preprocessing and Augmentation for Deep Learning
Preprocess data with deterministic operations such as normalization or color space conversion, or augment training data with randomized operations such as random cropping or color jitter.
- Datastores for Deep Learning (Deep Learning Toolbox)
Learn how to use datastores in deep learning applications.
- Prepare Datastore for Image-to-Image Regression (Deep Learning Toolbox)
This example shows how to prepare a datastore for training an image-to-image regression network using the
- Augment Images for Deep Learning Workflows
This example shows how you can perform common kinds of randomized image augmentation such as geometric transformations, cropping, and adding noise.
Create Neural Networks for Image Processing Applications
- Train and Apply Denoising Neural Networks
Use a pretrained neural network to remove Gaussian noise from a grayscale image, or train your own network using predefined layers.
- Create Modular Neural Networks
You can create and customize deep learning networks that follow a modular pattern with repeating groups of layers, such as U-Net and cycleGAN.
- Get Started with GANs for Image-to-Image Translation
Transfer styles and characteristics from one set of images to the scene content of other images by using generative adversarial networks (GANs).
- Pretrained Deep Neural Networks (Deep Learning Toolbox)
Learn how to download and use pretrained convolutional neural networks for classification, transfer learning and feature extraction.
- List of Deep Learning Layers (Deep Learning Toolbox)
Discover all the deep learning layers in MATLAB®.
Deep Learning in MATLAB
- Deep Learning in MATLAB (Deep Learning Toolbox)
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.
- Semantic Segmentation Using Deep Learning (Computer Vision Toolbox)
This example shows how to segment an image using a semantic segmentation network.