Assiut University

Faculty of Computers & Information

Computer Science Department
Quality Assurance Unit

Introduction to Computer Vision

Course Specifications 2011-2012

Relevant program B.Sc. in Computers and Information

(Computer Science)
Department offers the program Computer Science
Department offers the course Computer Science
Academic year 4th Year
Date of specification approval 24/9/2012

A. Basic Information
1. Course Title: Introduction to Computer Vision
2. Course Code: CS427
3. Course hours per week:
Lecture Tutorial / Practical Total
3 2 5

B. Professional Information
1. Overall aims of the course
Upon completing this course the student will have learned, through
appropriate classroom and laboratory experiences, the following.
 Understanding cameras and projection models
 Low-level image processing methods such as edge detection
 Mid-level vision topics such as segmentation
 High-level vision tasks such as object recognition and 3D shape
reconstruction.

CS Program – 4th Year (2nd Semester) Page 8-1

 2. Intended Learning Outcomes (ILOs) of the course
a. Knowledge and Understanding Skills
On successful completion of the course, graduates should be able to:
a1. Understand the essential mathematics relevant to computer vision.
a2. Use high-level programming languages.
a3. Show a critical understanding of the principles of image and object recognition.

b. Intellectual Skills
On successful completion of this course, graduates should be able to:
b1. Define traditional and nontraditional computer vision problems, set goals
towards solving them, and observe results.
b2. Perform comparisons between (algorithms, methods, techniques...etc).
b3. Identify attributes, components, relationships, patterns, main ideas, and errors.
b4. Solve computer vision problems with pressing commercial or industrial
constraints.

c. Professional and Practical Skills

On successful completion of this course, graduates should be able to:
c1. Use appropriate programming languages.
c2. Evaluate computer vision systems in terms of general quality attributes and
possible tradeoffs presented within the given problem.
c3. Apply the principles of human-computer interaction to the evaluation and
construction of computer vision systems.

d. General and Transferable Skills

On successful completion of this course, graduates should be able to:
d1. Manage tasks effectively.
d2. Manage one's own learning and development, including time management.
d3. Search for information and adopt life-long self-learning.
d4. Communicate effectively by oral, written and visual means.
d5. Work effectively as an individual and as a member of a team.

3. Contents
No. of hours
No Topic taught ILOs
Lecture Tut/Prac
1 Introduction to the theory and b1, b3, c2, d3
3 −
application of computer vision.
2 Biological vision system, image a1, a3, b2, b3, d1, d2,
formation, image noise, binary 6 4 d3, d4, d5
images, gray images, color images
3 low-level image processing a1, a2, a3, b2, b3, c1,
12 8
methods such as edge detection d1, d2, d3, d4, d5
4 mid-level vision topics such as a1, a2, a3, b2, b3, c1,
segmentation, and line and curve 12 10 d1, d2, d3, d4, d5
detection
5 high-level vision tasks such as a1, a2, a3, b1, b3, b4,
object recognition and 3D shape 9 6 c1, c2, c3, d1, d2, d3,
reconstruction techniques d4, d5

CS Program – 4th Year (2nd Semester) Page 8-2

 4. Teaching and Learning Methods
4a. Lectures
4b. Tutorial Exercises
4c. Practical Exercises
4d. Projects
4e. Case Study

5. Student Assessment
5a. Tools
Final Exam To measure knowledge, understanding, intellectual and
professional skills.
Practical Exam To measure professional and general skills
Class Work To measure the participation of the student during the tutorial,
professional and general skills.
Projects To measure professional and general skills

5b. Time Schedule

Assessment Week No
Final Exam 16
Practical Exam 15
Projects 12-14

5c. Grading System

The students’ points are calculated through the following point distribution.
Assessment Grade %
Final Exam 70%
Practical Exam 10%
Project and/or Assignments 10%
Class Work 10%
Then, the passing and failing grades are evaluated from the student achievement
point “X” based on the following table.
Very Poor Poor Pass Good Very Good Distinguished
0% ≤ X < 30% 30% ≤ X < 50% 50% ≤ X < 65% 65% ≤ X < 75% 75% ≤ X < 85% 85% ≤ X ≤ 100%

6. List of References
6a. Course Notes
o Short course notes available at doctor’s office.
6b. Required Books (Textbooks)
o Bogusław Cyganek, J. Paul Siebert, "An Introduction to 3D Computer
Vision Techniques and Algorithms", John Wiley & Sons, 2009.
6c. Recommended Books
o David A. Forsyth, Jean Ponce, "Computer Vision: A Modern Approach",
Prentice Hall, 2002.

CS Program – 4th Year (2nd Semester) Page 8-3

 7. Facilities Required for Teaching and Learning
 A lecture hall is equipped with a projector and a computer.
 Labs are equipped with computers and Internet facilities.
 Tutorial rooms are equipped with projectors and computers.
 A library.

Course Coordinator: Dr. Khaled F. Hussain

Signature:

Date: 24/9/2012

Department Head: Dr. Abdel-Rahman Hedar

Signature:

Date: 24/9/2012

CS Program – 4th Year (2nd Semester) Page 8-4

 Course Matrix
Course Name Introduction to Computer Vision Course Code CS427

Teaching and Learning

ILOs Assessment Tools
Methods

Practical Exercises
Tutorial Exercises

Data Collections

Mid-Term Exam

Practical Exam

Criteria
Teaching

Class Work
Workshops

Case Study

Final Exam

Oral Exam
Course Aims Course Content

Lectures

Projects
Weeks
a’s b’s c’s d’s

•Understanding cameras and Introduction to the theory and

Student evaluation, course file, exam results

projection models application of computer 1 − 1, 3 2 3     
•Low-level image processing vision.
methods such as edge Biological vision system,
image formation, image noise,
detection
binary images, gray images,
2-3 1, 3 2, 3 − 1-5         
•Mid-level vision topics such color images
as segmentation low-level image processing
•High-level vision tasks such methods such as edge 4-7 1-3 2, 3 1 1-5         
as object recognition and 3D detection
shape reconstruction. mid-level vision topics such
as segmentation, and line and 8-11 1-3 2, 3 1 1-5         
curve detection
high-level vision tasks such as
object recognition and 3D
shape reconstruction
12-14 1-3 1, 3, 4 1, 2, 3 1-5         
techniques

Course Coordinator Dr. Khaled F. Hussain Department Head Dr. Abdel-Rahman Hedar
Signature Signature

CS Program – 4th Year (2nd Semester) Page 8-5

CS Program – 4th Year (2nd Semester) Page 8-6