Please join Mathworks for a free MATLAB seminar at Vanderbilt University on Tuesday, November 27th.
- Presenter: Brett Shoelson, Ph. D., Principle Application Engineer, Mathworks
- When: Tuesday, November 27th, 12:30 - 2:00 p.m.
- Where: Featheringill Hall, Room 129
- Topic: From Pixels to Features to Learning Models: Image Processing, Computer Vision, and Machine/Deep Learning with Images in MATLAB
Transitioning image models from pixel-based to feature-based allows us to extract information from images and video at a high level, to detect, classify, and track objects, co-register images, or understand a real-world scene. Using collections of features, we can train computers to recognize objects, with user-specified or automatically determined features. In this session, you will learn about capabilities for image processing and computer vision with MATLAB. We will also describe approaches to implementing different models for machine learning, including using deep convolutional neural networks (CNNs).
Demos include:
- Perform automatic image registrations using feature-based approaches
- Detect, recognize, and track objects in images
- Ground truth images and video, and train new classifiers
- Use pre-built networks to create new recognizers in a “transfer-learning-based workflow”
Space is limited. Email Scott Benway at scott.benway@mathworks.com if you wish to attend.