Course Outline

CS-565 Computer Vision
FALL – 2015
CS-565 – Computer Vision
Instructor: Dr. Nazar Khan
Semester: Fall 2015
Campus: Allama Iqbal
Passing this course is necessary for students planning to register for an
M.Phil Thesis with Dr. Nazar Khan.
Course Description:
Human beings (and even animals) “look” at the real-world and extract extremely accurate
information extremely efficiently. Computers can fail catastrophically at this task! In this course
we look into why “Vision” is a difficult problem to solve and we go through successful,
mathematically well-founded techniques used to solve the Vision problem.
This course is a useful application of mathematical concepts from Linear Algebra and Calculus.
Therefore, the students could do well by brushing up on their Linear Algebra, Calculus and
programming skills before taking this class. The techniques learned here can be useful for other
areas such as Image Processing, Machine Learning, Artificial Intelligence and Computer
Who can register?
This course is open to graduate students as CS-565. It is also open to undergraduate students
as SE-461.
Class size will NOT exceed 40 students. Graduate students have top priority. Remaining seats
will be filled by undergraduates based on
2. FYP topic
3. Instructor's permission (only in exceptional circumstances).
To determine course grade, graduate students will be evaluated in a more rigorous manner.
CS-565 Computer Vision
FALL – 2015
Goals and Objectives:
1. General overview of the field of Image Analysis.
2. Learn fundamental techniques and mathematical models in the areas of Image Processing
and Computer Vision.
3. Understand typical Computer Vision pipelines for solving problems.
By the end of the semester, a student should:
not be afraid of Mathematics,
be able to develop Computer Vision applications,
explain fundamental algorithms in the area along-with their mathematical subtleties,
appreciate that Computer Vision is a deceptively hard problem,
be equipped to read research papers in the area,
report results in a scientifically satisfactory manner, and
be comfortable enough with the terminology and techniques so as to pursue graduate
level research in the area.
Related Text / Reading Material:
We will not be following one particular reference. However, relevant material can be found in:
Image Processing
Digital Image Processing by R. C. Gonzalez, R. E. Woods.
Computer Vision
Introductory techniques for 3D Computer Vision by Trucco and Verri
Image Processing, Analysis, and Machine Vision by Milan Sonka, Vaclav Hlavac, Boyle Roger
Computer Vision: Algorithms and Applications (
Multiple View Geometry in Computer Vision by Hartly and Zisserman
Computer Vision: A Modern Approach by Forsyth and Ponce
Computer Vision by Linda G. Shapiro, George C. Stockman
CS-565 Computer Vision
Scheme of Study:
1. Introduction (1 Week)
a. Computer Vision vs. Image Processing vs. Computer Graphics
b. Computer Vision vs. Biological Vision – The Grand Deception!
c. Successful Computer Vision solutions.
2. Mathematical Background (1 Week)
a. Cartesian vs. Image axis
b. Taylor's formula
c. Constrained optimisation
d. SVD
3. Image Processing (4 Weeks)
a. Image Types and their degradations.
b. Color Perception and Color Spaces
c. Filtering and Convolutions
i. Gaussian Smoothing
ii. Derivative Filtering
d. Fourier Transform
i. Basic idea and background math
ii. Euler's formula for circular motion
iii. Projection onto circular motion basis
iv. Frequency domain filtering
e. Image Adjustment
4. 2D Computer Vision (5 Weeks)
a. Edge Detection
b. Corner Detection
c. Hough Transform
d. Spatial Transformations
i. Types of spatial transformations
ii. Recovering best transformation
iii. Image warping
e. Optical Flow
i. Local Methods
ii. Global Methods
5. 3D Computer Vision (3 Weeks)
a. Projective Geometry
i. Camera Models
ii. Camera Matrix Anatomy
iii. Camera Calibration
FALL – 2015
CS-565 Computer Vision
FALL – 2015
b. Stereo Reconstruction
i. The case of orthoparallel cameras
ii. The case of converging cameras
1. Epipolar constraint and fundamental matrix
2. Estimation of fundamental matrix
3. Disparity estimation
6. Machine Learning for Computer Vision (1 Week)
a. Principal Component Analysis
Grading Scheme/Criteria:
Grading Policy:
1. To determine course grade, graduate students will be evaluated in a more rigorous
2. Theoretical assignments have to be submitted before the lecture on the due date.
3. There will be no make-up for any missed quiz.
4. Make-up for a mid-term or final exam will be allowed only under exceptional
circumstances provided that the instructor has been notified beforehand.
5. Instructor reserves the right to deny requests for any make-up quiz or exam.
6. Worst score on quizzes will be dropped.
7. Worst score on assignments will be dropped.