Use segmentation to detect and analyze regions of interest in images & video

Apply spatial filters and morphological operators to improve segmentation & remove noise

Segment & analyze 3D images, such as MRI images of a brain

Use interactive tools to quickly test a variety of segmentation approaches & automatically generate code for reuse

Apply image processing algorithms to large sets of images & verify your algorithms generalize to new images

Apply image processing algorithms to video files

Analyze your image & video processing results, including calculating statistics like average area & identifying outliers

Complete a specialization-level project where you will detect cars in a noisy video

Use common algorithms for feature detection, extraction, & matching

Perform image registration by identifying control points & estimating geometric transformations

Complete a final project where you stitch together images from NASA’s Mars Curiosity Rover

Combine images with image stitching to create panorama images

Prepare data and create features for classifying images

Train & evaluate models to classify images using

Train & evaluate object detection machine learning models

Customize model training for different applications using cost matrices

Use pre-trained deep neural networks like YOLO to perform object detection

Use optical flow to detect motion & moving objects

Perform multi-object tracking to count, track, & determine the direction of objects

Develop a strong foundation in deep learning for image analysis

Retrain common models like GoogLeNet and ResNet for specific applications

Investigate model behavior to identify errors, determine potential fixes, and improve model performance

Complete a real-world project to practice the entire deep learning workflow

Retrain popular YOLO deep learning models for your applications

Visualize results to gain insights into model performance

Evaluate detection models by examining both class and location accuracy.

Analyze labeled images to identify and fix potential data shortcomings

Train and calibrate specialized models known as anomaly detectors

Generate synthetic training images for situations where acquiring more data is expensive or impossible

Use AI-assisted auto-labeling to save time and money

Import models from 3rd party tools like PyTorch and export your model outside of MATLAB