Image Processing Toolbox

Perform image processing, visualization, and analysis 


Image Processing Toolbox™ provides a comprehensive set of reference-standard algorithms and workflow apps for image processing, analysis, visualization, and algorithm development. You can perform image segmentation, image enhancement, noise reduction, geometric transformations, image registration, and 3D image processing.

Image Processing Toolbox apps let you automate common image processing workflows. You can interactively segment image data, compare image registration techniques, and batch-process large data sets. Visualization functions and apps let you explore images, 3D volumes, and videos; adjust contrast; create histograms; and manipulate regions of interest (ROIs).

You can accelerate your algorithms by running them on multicore processors and GPUs. Many toolbox functions support C/C++ code generation for desktop prototyping and embedded vision system deployment.

Get Started:

Exploration and Discovery

Use apps and functions to acquire, visualize, analyze, and process images in many data types.

Acquiring and Importing Data

Import images and video generated by a wide range of devices, including webcams, digital cameras, satellite and airborne sensors, medical imaging devices, microscopes, telescopes, and other scientific instruments. 

Support for a number of specialized image file formats. For medical images, it supports DICOM files, including associated metadata, as well as the Analyze 7.5 and Interfile formats.

Display High Dynamic Range Image

Apps for Exploration and Discovery

Use apps to explore and discover various algorithmic approaches. With the Color Thresholder app, you can segment an image based on various color spaces. The Image Viewer app lets you interactively place and manipulate ROIs, including points, lines, rectangles, polygons, ellipses, and freehand shapes.

Color-Based Segmentation

Image Preprocessing

Increase the signal-to-noise ratio and accentuate image features using custom or predefined filters.

Image Enhancement

Increase the signal-to-noise ratio and accentuate image features by modifying the colors or intensities of an image. Perform convolution and correlation, remove noise, adjust contrast, and remap the dynamic range.

Enhancing Multispectral Color Composite Images

Morphological Operators

Enhance contrast, remove noise, thin regions, or perform skeletonization on regions.

Granulomety of Snowflakes

Image Deblurring 

Correct blurring caused by out-of-focus optics, movement by the camera or the subject during image capture, atmospheric conditions, short exposure time, and other factors. 

Deblurring Images Using the Blind Deconvolution Algorithm

3D Image Processing Workflows

Visualize and perform complete image processing workflows on 3D volumes.

3D Visualization

Explore a 3D volume by using different visualization methods to explore the structure of the data. You can map the pixel intensity of a 3D volume to opacity to highlight a specific region within the volume.

3D Processing

Use many 3D-specific functions in addition to ND functions that enable complete image processing workflows with 3D data.

3D Segmentation

Use programmatic functions and interactive apps to perform 3D segmentation. You can use thresholding, active contours, semantic segmentation and other techniques to perform segmentation of 3D Data.

Image Analysis

Extract meaningful information from images, such as finding shapes, counting objects, identifying colors, or measuring object properties.

Edge Detection

Identify object boundaries in an image using pre-built algorithms. These algorithms include the Sobel, Prewitt, Roberts, Canny, and Laplacian of Gaussian methods.

Image Region Analysis

Calculate the properties of regions in images, such as area, centroid, and orientation. Use the Image Region Analysis App to automatically count, sort, and remove regions based on properties.

Image Region Analyzer App

Hough Transform, Statistical Functions, and Color Space Conversions

Find line segments, line endpoints, and circles. Statistical functions let you analyze the characteristics of an image. Color-space conversion accurately represents color independently from devices.

Detect and Measure Circular Objects in an Image

Image Segmentation

Explore different approaches to image segmentation, including automatic thresholding, edge-based methods, and morphology-based methods.

Image Segmentation Techniques

Determine region boundaries in an image and explore different approaches to image segmentation. Use segmentation apps to explore these techniques interactively.

Watershed Segmentation

Use watershed segmentation to separate touching objects in an image. The watershed transform is often applied to this problem.

Marker-Controlled Watershed Segmentation

Image Registration

Align images to enable quantitative analysis or qualitative comparison.

Image Registration Methods

Use intensity-based image registration, which automatically aligns images using relative intensity patterns. Perform multimodal 3D registration and non-rigid registration, and visually inspect results by creating composite images that highlight misalignments.

Acceleration and Deployment

Work with C/C++ and HDL code; run image processing algorithms on PC hardware, FPGAs, and ASICs; and develop imaging systems.

Target Hardware

Automatically generate C, C++, and HDL code. Many image processing functions support code generation, so you can run image processing algorithms on PC hardware, FPGAs, ASICs, and embedded hardware.

GPU Acceleration 

Use GPUs and multicore processors to improve your application and model performance.

Marker-Controlled Watershed Segmentation

Latest Features

Volume Segmenter App

Segment 3-D grayscale or RGB volumetric images

Deep Learning

Resize 2-D and 3-D input layers and spatial dimensions of deep learning arrays by a scale factor or to a specified size

Image Quality Metrics

Measure image color using X-Rite ColorChecker test chart

Color Error

Calculate color differences using CIE76, CIE94, or CIEDE2000 standard

DICOM-RT Contours

Create volumetric mask from contour data

See release notes for details on any of these features and corresponding functions.

MATLAB for Deep Learning

With just a few lines of MATLAB code, you can apply deep learning techniques to your work whether you’re designing algorithms, preparing and labeling data, or generating code and deploying to embedded systems.