Course Identification

Introduction to computer vision
20224011

Lecturers and Teaching Assistants

Prof. Ronen Basri, Prof. Michal Irani, Prof. Shimon Ullman
Ganit Kupershmidt, Itai Antebi, Roy Abel, Michal Skoury

Course Schedule and Location

2022
First Semester
Sunday, 14:15 - 16:00, Ziskind, Rm 1
31/10/2021
18/03/2022

Field of Study, Course Type and Credit Points

Mathematics and Computer Science: Lecture; Elective; Regular; 2.00 points
Life Sciences: Lecture; Elective; Regular; 2.00 points
Life Sciences (Brain Sciences: Systems, Computational and Cognitive Neuroscience Track): Lecture; Elective; Regular; 2.00 points

Comments

This course is *mandatory* for all students who will later wish to take the course "Advanced Topics in Computer Vision and Deep Learning" in the second semester (unless you took an equivalent formal introductory course in Computer Vision in another university, and can point us to it). Also, if you wish to pursue a thesis in the field of Computer Vision in your second year, it is highly recommended that you take this course, as you will need knowledge of this material.

Prerequisites

Students in this course are highly encouraged to take the following course:

  • H. Dym, Basic Topics I, which is offered in the first Semester.

In addition, taking courses in the following topics is recommended for people interested in Vision:

  • Machine-Learning
  • Optimization

Restrictions

50

Language of Instruction

English

Attendance and participation

Required in at least 80% of the lectures

Grade Type

Numerical (out of 100)

Grade Breakdown (in %)

40%
60%
The total grade will be based on 40-50% exercises, and 50-60% exam

Evaluation Type

Examination

Scheduled date 1

06/02/2022
Ziskind, Rm 1
1000-1300
N/A

Scheduled date 2

16/03/2022
Ziskind, Rm 1
1400-1700
N/A

Estimated Weekly Independent Workload (in hours)

N/A

Syllabus

This course will cover basic topics in Computer Vision, Image Processing, and Human Vision,
including basic Fourier analysis, 3D shape recovery from stereo images, motion and video analysis, illumination, and object recognition.

Learning Outcomes

Upon successful completion of this course students should be able to:

  1. Demonstrate understanding of basic computer vision problems.
  2. Apply solution algorithms to basic computer vision problems.
  3. Demonstrate understanding of supervised machine learning in the context of computer vision.

Reading List

  1. E. Trucco, A. Verri. Introductory Techniques for 3-D Computer Vision. Prentice Hall, 1998.
  2. D. A. Forsyth, J. Ponce. Computer Vision a Modern Approach. Prentice Hall, 2003.
  3. R. Szeliski, Computer Vision: Algorithms and Applications. This book draft is currently available online.
  4. Rafael C. Gonzalez, R.E.Woods, Ralph C. Gonzalez. Digital Image Processing. Addison-Wesley, 1992 .
  5. R. Hartley, A.Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, 2000.
  6. Burt, P., and Adelson, E. H., The Laplacian Pyramid as a Compact Image Code. IEEE Transactions on Communication, 31:532-540, 1983.

Website

N/A