Class Description
This course in the techniques of machine vision and the challenges that are faced when an artificial system is used to mimic the human visual system. This computation class will provide a base for students to build on in the field of artificial vision and the systems to address problems that are encountered when using a classifier to discriminate between multiple sets of biological samples that only exhibit slight differences. Also uses for this type of technology from the pharmaceutical industry to everyday life.
The topics covered in the course include:
-
Overview of problems of machine vision and pattern classification
-
Image formation and processing
-
Feature extraction from images
-
Biological object recognition
-
Bayesian Decision Theory
-
Clustering
Applications
Some of problems that machine vision systems are designed to solve include:
The course will have a strong hands-on component. Some additional reading from current research will be provided.
Requirements
-
Problem sets
-
Paper presentation
-
Final project
Prerequisites
Basic Linear Algebra
Probability
Calculus
Textbooks
Duda, Hart and Stork, Pattern Recognition. Wiley-Interscience, 2000.
Mallot, Computational Vision: Information Processing in Perception and Visual Behavior. Cambridge, MA: MIT Press, 2000.
Stan
Stan is a computer system at MIT that many of the problems will be done on. This computer is only available to students enrolled in this class.