ECE: Electrical & Computer Engineering

ECE 5554 Theory and Design of Computer Vision Systems

Spring 2014 textbook list

The Spring 2014 ECE textbook list is available online for students.

Current Prerequisites & Course Offering

For current prerequisites for a particular course, and to view course offerings for a particular semester, see the Virginia Tech Course Timetables.

Return to course list

ECE 5554 Theory and Design of Computer Vision Systems (3C)

Analysis of digital images and three-dimensional scenes. Image acquisition, representation of two- and three-dimensional shapes, visual cues for range estimation. Image filtering and histogram-based analysis for image enhancement, noise suppression, edge detection, region detection, and image segmentation. Introduction to such topics as visual texture, stereo vision, structured-light ranging, and motion analysis.

What is the reason for this course?

Computers of the future will require the ability to interact more readily with the three-dimensional world. Although the ability to "see" is easy for humans, it has proven remarkably difficult to develop vision-related algorithms for a machine. This course introduces issues and approaches that are needed in this area. Applications of computer vision include autonomous vehicle navigation, industrial automation, robotics, content-based search in image databases, face and gesture recognition, and aids for the seeing-impaired.

Typically offered: Fall. Program Area: Computers.

Prerequisites: Prerequisites: STAT 4714.

Why are these prerequisites or corequisites required?

The course assumes knowledge of basic probability theory, as introduced in STAT 4714.

Department Syllabus Information:

Major Measurable Learning Objectives:
  • select imaging devices and illumination sources for a given application;
  • design and implement algorithms that perform edge detection, noise suppression, image thresholding, histogram analysis, region detection, and region labeling;
  • compute edge and region properties that can be used for higher-level analysis;
  • analyze problems that involve perspective projection or orthographic projection; and
  • assess the performance of vision-based range- and shape-estimation systems.

Course Topics
Topic Percentage
Image formation, acquisition, and representation 15%
Image statistics, histogram analysis, thresholding 15%
Region detection and labeling, region properties, thinning 15%
Window-based operations, smoothing, edge detection 15%
Range and shape estimation using such cues as texture, stereo disparity, motion, and defocus blur 20%
Shape representation, curvature analysis 10%
Interpretation of line drawings 10%

Return to course list