Image Processing Using Deep Learning

Extend deep learning workflows with image processing applications

Apply deep learning to image processing applications by using Deep Learning Toolbox™ together with Image Processing Toolbox™.

Functions

augmentedImageDatastoreTransform batches to augment image data
randomPatchExtractionDatastoreDatastore for extracting random 2-D or 3-D random patches from images or pixel label images
bigimageDatastoreDatastore to manage blocks of big image data

Topics

Preprocess Data for Domain-Specific Deep Learning Applications

Perform deterministic or randomized data processing for domains such as image processing, object detection, semantic segmentation, signal and audio processing, and text analytics.

Augment Images for Deep Learning Workflows Using Image Processing Toolbox

This example shows how MATLAB® and Image Processing Toolbox™ can perform common kinds of image augmentation as part of deep learning workflows.

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.

Featured Examples

Single Image Super-Resolution Using Deep Learning

Single Image Super-Resolution Using Deep Learning

Train a Very-Deep Super-Resolution (VDSR) neural network, then use a VDSR network to estimate a high-resolution image from a single low-resolution image.

Open Live Script
JPEG Image Deblocking Using Deep Learning

JPEG Image Deblocking Using Deep Learning

Train a denoising convolutional neural network (DnCNN), then use the network to reduce JPEG compression artifacts in an image.

Open Live Script
Image Processing Operator Approximation Using Deep Learning

Image Processing Operator Approximation Using Deep Learning

Approximate an image filtering operation using a multiscale context aggregation network (CAN).

Open Live Script
Develop Raw Camera Processing Pipeline Using Deep Learning

Develop Raw Camera Processing Pipeline Using Deep Learning

Convert raw camera data to an aesthetically pleasing color image using a U-Net.

Open Live Script
Deep Learning Classification of Large Multiresolution Images

Deep Learning Classification of Large Multiresolution Images

Train an Inception-v3 deep neural network to classify multiresolution whole slide images (WSIs) that do not fit in memory.

Open Live Script
Semantic Segmentation of Multispectral Images Using Deep Learning

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

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
Remove Noise from Color Image Using Pretrained Neural Network

Remove Noise from Color Image Using Pretrained Neural Network

Remove Gaussian noise from an RGB image. Split the image into separate color channels, then denoise each channel using a pretrained denoising neural network, DnCNN.

Open Live Script
Neural Style Transfer Using Deep Learning

Neural Style Transfer Using Deep Learning

Apply the stylistic appearance of one image to the scene content of a second image using a pretrained VGG-19 network [1]. This example uses the distinctive Van Gogh painting "Starry Night" as the style image and a photograph of a lighthouse as the content image.

Open Live Script
Train Fast Style Transfer Network

Train Fast Style Transfer Network

Train a network to transfer the style of an image to a second image. It is based on the architecture defined in [1].

Open Live Script

Deep Learning Toolbox Documentation

Support