CCS is pleased to announce that MathWorks will again be offering two complimentary workshops on Monday February 9th. These sessions are independent of each other and will teach two different sets of skills. You may register for one or both, but please note that the morning session will be hosted in the College of Engineering on the Coral Gables campus, and the afternoon session will be held at the Miller School of Medicine. Register here.
Medical Image Processing with MATLAB
Monday, February 9, 2015 | 9:00 AM – 11:30 AM
College of Engineering, Room MEA 202
Using MATLAB products you can read and write DICOM images, automate acquisition
of images and video from imaging hardware, create custom visualizations for images
and video sequences, develop new ideas using a library of reference-standard
algorithms and create scripts to automate repetitive tasks.
Using MATLAB to import, analyze and visualize medical images, and to explore ideas
and automate your workflow. Highlights may include:
- Quantifying regions in medical images to extract meaningful information
- Developing algorithms and applications to automate your workflow
- Volume visualization from a brain MRI image stack
- Measurement of vessel tortuosity
- Video analysis and neural network-classification of a fluorescein angiogram
Machine Learning with MATLAB
February 9; 1:30 PM – 4:00 PM
Batchelor Children’s Research Institute, Room 508A & B
Miller School of Medicine
Machine learning techniques are used frequently to “learn” the appearance of objects
of interest to create more robust and discriminative algorithms. Machine learning is
also used to find patterns in large collections of images and to cluster similar objects.
Existing MATLAB users will learn about new features for pattern classification, data
regression, feature extraction, face detection and face recognition.
In this presentation, discover how to use machine learning techniques to solve
practical computer vision problems including:
- Match objects in live video to visually similar objects from a database using
- feature extraction and matching
- Create an object detector to detect and locate humans in images
- Perform facial recognition to match an image of a face to an existing
- database using dense feature extraction