Image Processing and Computer Vision

Acquire, process, and analyze images and video for algorithm development and system design

With image processing and computer vision products from MathWorks^®, you can perform end-to-end processing workflows from data acquisition and preprocessing, to enhancement and analysis, through deployment onto embedded vision systems.

These products enable a large variety of workflows for image, video, point cloud, lidar, and hyperspectral data. Using these products, you can:

Interactively visualize, explore, and process data using apps.
Enhance and analyze data algorithmically.
Perform semantic segmentation, object detection, classification, and image-to-image translation using deep learning.
Interface with hardware for image acquisition, algorithm acceleration, desktop prototyping, and embedded vision system deployment.

Products for Image Processing and Computer Vision

Image Processing Toolbox

Perform image processing, visualization, and analysis

Computer Vision Toolbox

Design and test computer vision, 3D vision, and video processing systems

Lidar Toolbox

Design, analyze, and test lidar processing systems

Medical Imaging Toolbox

Visualize, register, segment, and label 2D and 3D medical images

Topics

Preprocess and Label Data

Choose an App to Label Ground Truth Data (Computer Vision Toolbox)
Decide which app to use to label ground truth data: Image Labeler, Video Labeler, Ground Truth Labeler, Lidar Labeler, Signal Labeler, or Medical Image Labeler.
Preprocess Data for Domain-Specific Deep Learning Applications (Deep Learning Toolbox)
Perform deterministic or randomized data processing for domains such as image processing, object detection, semantic segmentation, signal and audio processing, and text analytics.
Getting Started with Point Clouds Using Deep Learning (Computer Vision Toolbox)
Understand how to use point clouds for deep learning.
Approaches to Registering Images (Image Processing Toolbox)
Choose from four approaches to image registration: the Registration Estimator app, intensity-based automatic image registration, control point registration, and automated feature matching.

Detect Objects and Features

Getting Started with Object Detection Using Deep Learning (Computer Vision Toolbox)
Object detection using deep learning neural networks.
Local Feature Detection and Extraction (Computer Vision Toolbox)
Learn the benefits and applications of local feature detection and extraction.
Match and Visualize Corresponding Features in Point Clouds (Lidar Toolbox)
This example shows how to match corresponding features between point clouds using the pcmatchfeatures function and visualize them using the pcshowMatchedFeatures function.

Segment Images

Getting Started with Semantic Segmentation Using Deep Learning (Computer Vision Toolbox)
Segment objects by class using deep learning.
Getting Started with Image Segmenter (Image Processing Toolbox)
Segment an image using different techniques, refine and save the binary mask, and export the segmentation code by using the Image Segmenter app.
Segment Image and Create Mask Using Color Thresholder (Image Processing Toolbox)
Segment an image based on color values and create a binary mask image using Color Thresholder.

Enhance Images

Get Started with GANs for Image-to-Image Translation (Image Processing Toolbox)
Transfer styles and characteristics from one set of images to the scene content of other images by using generative adversarial networks (GANs).
Contrast Enhancement Techniques (Image Processing Toolbox)
Adjust the contrast of grayscale and color images using intensity value mapping, histogram equalization, and contrast-limited adaptive histogram equalization.
Noise Removal (Image Processing Toolbox)
Remove image noise by using techniques such as averaging filtering, median filtering, and adaptive filtering based on local image variance.

Perform Simultaneous Localization and Mapping

Choose SLAM Workflow Based on Sensor Data (Computer Vision Toolbox)
Choose the right simultaneous localization and mapping (SLAM) workflow and find topics, examples, and supported features.

Acquire and Calibrate Data

Get Started with Image Acquisition Explorer (Image Acquisition Toolbox)
Use the Image Acquisition Explorer to preview, configure, acquire, and save image data.
Using the Single Camera Calibrator App (Computer Vision Toolbox)
Estimate camera intrinsics, extrinsics, and lens distortion parameters.
What Is Lidar-Camera Calibration? (Lidar Toolbox)
Fuse lidar and camera data.

Deploy on Hardware

Code Generation for Image Processing (Image Processing Toolbox)
Learn how to generate C code from Image Processing Toolbox™ functions using MATLAB^® Coder™.
GPU Code Generation Workflow (GPU Coder)
Design, implement, and verify generated CUDA MEX for acceleration and standalone CUDA code for deployment.

Related Information

Featured Examples

Resize an Image

Change the size of an image by specifying a multiplicative scale factor or by specifying the desired output size of the image.

Detect and Count Cell Nuclei in Whole Slide Images

Use color thresholding and region property analysis, while working with small blocks of image data, to detect nuclei in WSIs.

Automatically Detect and Recognize Text Using Pretrained CRAFT Network and OCR

Perform text recognition by using a deep learning based text detector and OCR. In the example, you use a pretrained CRAFT (character region awareness for text) deep learning network to detect the text regions in the input image. You can modify the region threshold and the affinity threshold values of the CRAFT model to localise an entire paragraph, a sentence, or a word. Then, you use OCR to recognize the characters in the detected text regions.

Detect Image Anomalies Using Explainable FCDD Network

Use an anomaly detector to distinguish between normal pills and pills with anomalous chips or contamination.

Detect, Classify, and Track Vehicles Using Lidar

Detect, classify, and track vehicles by using lidar point cloud data captured by a lidar sensor mounted on an ego vehicle.

Cardiac Left Ventricle Segmentation from Cine-MRI Images Using U-Net Network

Segment 2-D cardiac MRI images using U-Net, and explore predictions using Grad-CAM explainability maps.