Scribd
Upload
28 views

Computer Vision Course Outline

Uploaded by

Jay Grey
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
28 views

Computer Vision Course Outline

Uploaded by

Jay Grey
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

UNIVERSITY OF GHANA

(All rights reserved)

DEPARTMENT OF COMPUTER SCIENCE

SCHOOL OF PHYSICAL AND APPLIED SCIENCES

SEMESTER 1, 2023/2024 ACADEMIC YEAR

COURSE SYLLABUS

DCIT412: Computer Vision

Credits: 3 hours

Lecture Period (s) and Venue: Tuesday 5:30pm-7:20pm (Math 19); Wednesday 3:30pm-4:20pm (Math 5)

Prerequisites: No prerequisite

Course Instructor:
• Name: Prof. Ebenezer Owusu
• Office Location: CS 4, Department of Computer Science
• Office Hours: Friday 10:00am-2:00pm
• E-mail: [email protected] / [email protected]
Teaching Assistant:
• Gifty Arthur
• Emmanuella Nana Akua Asante
Course Description:
The course can be taken without any prior knowledge of computer vision or deep learning, but it does assume
some familiarity with machine learning concepts, and relevant mathematics and programming skills. The course
delivers both theoretical and practical knowledge, and by the end you should be able to understand, design, and
implement computer vision techniques for many real-world problems.

Computer Vision is a field of study that teaches computers how to 'see'. This means, how to go from the pixels in
an image to the information that a human can describe when they see a picture, much like self-driving cars,
autonomous robots, or social media apps that recommend images or videos based on your preferences. This course
is an in-depth introduction to the field of Computer Vision.

The course is structured around different problems in computer vision, such as object recognition and video
classification, and covers both classical and deep learning approaches.

The course can be taken without any prior knowledge of computer vision or deep learning, but it does assume
some familiarity with machine learning concepts, and relevant mathematics and programming skills. The course
delivers both theoretical and practical knowledge, and by the end you should be able to understand, design, and
implement computer vision techniques for many real-world problems.

Course Objective:
The course delivers both theoretical and practical knowledge, and by the end you should be able to:

• Denoise a digital image.


• Segment different images.
• Extract main keypoints from a digital image.
• Design and implement computer vision techniques for many real-world problems.

Learning Outcomes:
The following are the specific learning outcomes that students are expected to achieve at the end of the course:

• Image Representation
• Image Processing Development tools
• Human Visual Perception
• Transform and Spatial Filters, Wavelet transform.
• Image Enhancement
• Object Detection
• Image Compression

Course Delivery:
The mode of course delivery is outlined as follows:

• Lectures
• Practical work
• Tutorials
• Presentations
Plagiarism policy
Plagiarism in any form is unacceptable and shall be treated as a serious offence. Appropriate sanctions, as
stipulated in the Plagiarism Policy, will be applied when students are found to have violated the Plagiarism Policy.
The policy is available at http://www.ug.edu.gh/aqau/policies-guidelines. ALL students are expected to
familiarize themselves with the contents of the Policy.

Assessment and Grading:


• Class attendance: 5%
• Assignments/Quizzes: 15%
• Interim Assessment: 20%
• Presentation and Class Participation: 20%
• Final exam: 40%

Grading Scale:
Refer to Undergraduate Handbook

Reading List:
• Kinser, J. M. (2018). Image Operators: Image Processing in Python. CRC Press.
• Gonzalez, R. C. (2009). Digital image processing. Pearson education india.
• Chityala, R., & Pudipeddi, S. (2020). Image processing and acquisition using Python. Chapman and
Hall/CRC.
• Solomon, C., & Breckon, T. (2011). Fundamentals of Digital Image Processing: A practical approach with
examples in Matlab. John Wiley & Sons.
• Unger Holtz, T. S. (2007). Introductory digital image processing: A remote sensing perspective.

Other Information
• Attendance is compulsory. A student scores zero when fails to attend lectures.
• Caveat/disclaimer: This course outline is subject to modification/review anytime the lecturer sees
the need to do so.

Course Delivery plan/Schedule

Week Lecture # Topic Comments

1 Lecture Introduction Assignment


(Course Outline)
2 Lecture and Practical Image Formation (Camera Practical assignment
types, Projection, light)

3 Lecture / practicals Image Processing Assignment


(Convolution, filtering,
effects)
4 Lecture and practical Linear filters

5 Lecture and practical Traditional pipeline


(Interest points, descriptors,
matching)
6 Lecture and practical Object classification e.g. interim assessment,
quiz will be given on this
date

7 Lecture and practical Object Segmentation

8 Lecture Optical flow

9 Lecture and practical Project Presentation Student’s presentations

10 Depth Estimation

11 Humans (Pose and Shape


estimation)

You might also like