Prerequisites: Grade of C or better in MATH 203 / Linear Algebra, STAT 344 / Probability and Statistics for Engineers and Scientists I, and CS 310 / Data Structures.
Instructor: Prof. Harry Wechsler firstname.lastname@example.org
Course Description – This course covers basic principles of visual perception including image formation, image processing, image segmentation, motion, and tracking, machine learning and pattern recognition, and object detection and recognition from single images and/or streaming video. Students complete projects involving real images (e.g., biometrics / face recognition).
Course (ABET) Outcomes:
- Basic knowledge of image formation process.
- Basic knowledge of image processing techniques for color and gray level images: edge detection, corner detection, segmentation.
- Basics of video processing, motion computation and 3D vision and geometry.
- Ability to implement basic vision algorithms using MATLAB and OpenCV (Open source computer vision library).
- Ability to apply the appropriate technique to a problem, write a project report and present the results in class.
Time, Day, and Venue: TR – Tuesday/Thursday, 12:00 – 1:15 pm
– Art and Design Building 2026
Office Hours: TR – Thursday, 1:30 – 2:15 pm or by appointment, ENGR 4448.
First day of classes: Tuesday, August 26
Columbus recess: no class on Tuesday, October 14
Thanksgiving recess: no class on Thursday, November 27
Last day of classes: Thursday, December 4
Final Exam: Thursday, December 11, 10:30 – 1:15 pm
Required Textbook: Concise Computer Vision, Reinhard Klette, Springer, 2014 (including slides):
Supplementary Textbook: A Practical Introduction to Computer Vision with OpenCV, Kenneth Dawson-Howe, Wiley, 2014.
1. Computer Vision: Algorithms and Applications, R. Szelisky, Springer, 2010, http://szeliski.org/Book/
2. Computer Vision, D. Ballard and C. Brown, Prentice Hall, 1982 http://homepages.inf.ed.ac.uk/rbf/BOOKS/BANDB/bandb.htm
LECTURES 1 – 14: Introduction, Motivation (Mercedes-Benz / Safe Driving, MATLAB and OpenCV, Frequency Analysis and Filters, Color, Image Formation and Lightness, illumination invariants using Self-Quotient Image (SQI), Image Processing, Low-Level Operators and Pyramids, Image Analysis, Bayes Rule, Performance Evaluation (ROC et al.), Hough Transform, and Image Morphology (Aug 26 – October 9) (ref: Chaps 1 – 3 textbook / slides, notes, and papers)
LECTURES 15 – 22: Image Segmentation, Mean Shift, Belief Propagation, Video Segmentation, Feature Detection, Selection, and Tracking, Object Detection, Machine Learning, Biometrics and Face Recognition (October 21 – November 20) (ref: Chaps 5, 9 – 10 textbook / slides, notes, and papers)
LECTURES 23 – 26: Cameras and Coordinates, Dense Optical Flow and Motion Analysis, and Stereo Matching (November 20 – December 2) (ref: Chaps. 6, 4, and 8 textbook / slides, notes, and papers).
CLOSED BOOK EXAMINATIONS
REVIEW for MIDTERM1: Thursday, October 9.
MIDTERM1: Thursday, October 16.
REVIEW for MIDTERM2: Thursday, November 13.
(Non-Cumulative) MIDTERM2: Tuesday, November 18
REVIEW for FINAL: Thursday, December 4.
(Cumulative) FINAL: Thursday, December 11.
Required Software: MATLAB and OpenCV. Homework and Term Project will require using MATLAB and OpenCV. You can buy a student version of MATLAB in Johnson center or use it remotely from ITE labs. OpenCV is a C/C++ open source computer vision library.
· Homework – 20%
· (Non-Cumulative) MidTerm1 and MidTerm2 – Thursday, October 16 & Tuesday, November 18 – 20 %
· Term Project – December 4 – 20 %
· (Cumulative) Final – Thursday, December 11 - 40 %
You are expected to abide by the GMU honor code. Homework assignments and exams are individual efforts. Information on the university honor code can be found at
Additional departmental CS information: http://cs.gmu.edu/wiki/pmwiki.php/HonorCode/CSHonorCodePolicies