CISD 412 – Computer Vision Spring 2025

Instructor:

Dr. Chuk Brown [email protected]

Catalog Description:

This course introduces students to the basics of Computer Vision (CV) which is a subset of
Artificial Intelligence that train computers to automatically process, extract and manipulate
visual data from images and videos.

Online Learning Environment

Students are required to activate and check their email accounts at least one week prior to the
start of class to receive preliminary information from the instructor for completing the course
orientation on the Los Rios eLearning website at canvas.losrios.edu.

This may be your first experience as an online student, and students who are most successful are
those who can work independently, are organized, practice good time management, speak up and
communicate clearly, and are comfortable with technology.

Complete the weekly “To-Do:” items on each week’s checklist BEFORE watching the
lectures. Assignments, quizzes and labs will be due the Thursday AFTER the lectures are
published.

Online Course Expectations

• Time Commitment: A rule of thumb for classroom courses is that you should expect to
spend 2 hours outside of class for every hour of lecture. If you were taking this course as
a 3 credit CIS course, you would have 3 hours of class time per week. Add to that 6
hours outside of class, and you get 9 hours per week. Keep in mind that this is an
average. Some weeks you may complete the work in less time. Other weeks it may take
longer. The actual amount of time a given student spends can also vary widely based on
differing experience with the course material. Be sure to budget your time wisely, and do
not wait until the last minute to start an assignment!
 • Attendance: You are required to watch each online lecture.
• Computer Problems: Having a computer that does not work, or problems with your
connection to the Internet, is not a valid excuse for not meeting during our scheduled time
or not turning in work. If your computer stops working correctly during the course, or
you cannot connect to the Internet, make other arrangements to complete the coursework.

Prerequisites

The following courses must have been completed with grades of “C” or better:

1. CISD 307 (Introduction to Machine Learning)

Learning Outcomes and Objectives

• understand the basics of Computer Vision (CV), types, and the theory behind it.
• understand Data Acquisition for Computer Vision.
• understand Data Exploration.
• understand the basics of OpenCV, applications, functions, and implementation.
• learn about Computer Vision application, facial recognition and object detection.

Computing Environment

You will need a webcam.

You will need access to several online resources, including:

• Google Collaboratory: https://colab.research.google.com/

Optional Textbook

1. Géron, Aurélien (2022). Hands-On Machine Learning with Scikit-Learn, Kara, and
TensorFlow: Concepts, Tools, Techniques to Build Intelligent Systems (3rd Edition).
O'Reilly Media, Inc. [ISBN: 978-1-098-12597-4]

CISD 412 Honor Code

• Learning this content can be hard. Computer science concepts can take time for some
students to grasp. Some students in computer science will submit work that is not their
own. In order to be successful in this class you must try to figure out the concepts
through experimentation. Do not be afraid to see what will happen, as this is how you
will learn. By copying other’s work, you are short-changing your own learning and
undermining the atmosphere of trust in our class.
• You are expected to submit your own work in this course. Specifically, attempting to take
credit for someone else’s work by turning it in as your own constitutes plagiarism, which
is a serious violation of the Los Rios Community College District academic integrity
policy. This does not mean that any discussion of assignments is somehow a violation of
 the integrity policy. In computer science courses, it is usually appropriate to ask for hints
and debugging help or to talk generally about problem-solving strategies and program
structure.
• You must not share your submission solutions with other students. Specifically, you
should not ask anyone to give you a copy of their work, or conversely, give your work to
another student who asks for it. Discuss ideas together, but do the work on your own.
• You must be prepared to explain any work you submit. Sometimes students make
superficial changes to work that is not their own in an attempt to obscure the
plagiarism. If you created the work yourself, you will be able to explain it. I may ask
you to modify a specific method or explain an algorithm you were expected to create. If
you are unable to do this, no credit will be given for the assignment.

Semester Schedule Overview

Module 00 is first week of Semester, which begins January 18, 2025. Module 00 will be posted
Wednesday January 15, 2025. Module 16 is the Final Exam which will be posted on Wednesday
May 14, 2025 and due by Tuesday May 20, 2025.

Module # Date Posted Topic Homework and Quiz Due

00 Wed Road Map for Student Due by 11:59pm on Tue

Success • Post on Intro Discussion
• Accept Syllabus Terms
• Assignment 00

01 Wed Introduction to Computer Due by 11:59pm on Tue

Vision • Quiz #1
• HW #1

02 Wed Mathematics for Computer Due by 11:59pm on Tue

Vision • Quiz #2
• HW #2

Self-Assessment 1of3

03 Wed Data Acquisition for Due by 11:59pm on Tue

Computer Vision • Quiz #3
• HW #3

04 Wed Data Exploration - Parts I Due by 11:59pm on Tue

&& II • Quiz #4
• HW #4

05 Wed Introduction to CNN Due by 11:59pm on Tue

• Quiz #5
• HW #5
06 Wed Building Blocks of CNN Due by 11:59pm on Tue
• Quiz #6
• HW #6

Self-Assessment 2of3

07 Wed Midterm (Modules 1-6) Due by 11:59pm on Tue

• Midterm

08 Wed Transfer Learning Due by 11:59pm on Tue

• Quiz #7
• HW #7

09 Wed Hands-On with OpenCV && Due by 11:59pm on Tue

YOLO • Quiz #8
• HW #8

10 Wed Hands-On with TensorFlow Due by 11:59pm on Tue

and Keras • Quiz #9
• HW #9

11 Wed GAN: Generative Due by 11:59pm on Tue

Adversarial Network • Quiz #10
• HW #10

12 Wed Introduction to Intel Due by 11:59pm on Tue

OpenVINO Toolkit • Quiz #11
• HW #11

Self-Assessment 3of3

13 Wed Edge AI and Computer Due by 11:59pm on Tue

Vision (IoT) - Parts I && II • Quiz#12
• HW #12

14 Wed Future of Computer Vision Due by 11:59pm on Tue

• Quiz #13
• HW #13

15 Wed Course Review & Final Due by 11:59pm on Tue

Preparation

16 Wed Final Exam Final Exam Due by 11:59pm on Tue

Course Feedback Survey

Grading

Grades are posted in Canvas and will be updated one week after the due dates. Please make sure
to learn how to view the graded rubrics.

Grades will be weighted as follows:

Lecture Knowledge Check: 10%

Responding to the embedded questions in the Knowledge Check is 5% of your total weighted
average. Points are based on answering correctly.

Homework Assignments: 40%

Homework assignments make up 40% of your total weighted average. Homework assignments
include a variety of activities, such as contributing to Discussion Boards, Writing Assignments,
Technical Demonstrations, and others. Instructions for completing these activities will be
provided when assigned.

Online Quizzes: 15%

Weekly online quizzes in Canvas make up 15% of your total weighted average. Quizzes are to
be completed after the lessons for the week. Each quiz is timed and you will have one attempt to
answer the questions. All online quizzes must be completed on your own. You may not copy or
look at another student’s work. Quizzes are due the Thursday following our weekly meeting.

Midterm Exam: 15%

The Midterm Exam makes up 15% of your total weighted grade. There will be no make-ups.

Final Exam: 20%

The Final Exam makes up 20% of your total weighted grade. There will be no make-ups.

Mid-Term and Final Exam Policies:

• May use a hand-written 1-side of paper note that you create.

• May NOT use external resources such as books or the Internet (including but not limited
to Google and links to other sites).
• May ONLY use the strategies that I've taught in the lectures.

Grading Scale:

A: 90-100%

B: 80-89%
C: 70-79%

D: 60-69%

F: < 60%

Attendance

This class complies with the attendance policy specified under the Folsom Lake College
Academic Policy and the specifications in the FLC Catalog. You are expected to watch all
published lectures. Demonstrate viewing of the recorded lectures by completing each Module
and marking progress as “Done” in Canvas. Failure to watch recorded lectures may result in
your being dropped from the class or given a grade of F. You may also be dropped or given an F
for excessive absences, which is defined by the district as 6% or more of the total class
meetings. The student is responsible for dropping classes they have stopped attending in order to
avoid penalties.

Absence is not an excuse for missed announcements and/or assignments and does not excuse due
dates for assignments.

Late Work Policy

Late work will not be accepted. To be successful in this course you will need to stay organized
and check the calendar for upcoming due dates.

However, in the spirit of compassion for life's unexpected events and to avoid penalizing for
disruptions beyond our control, I will drop your lowest weekly quiz+homework score at the end
of the semester.

DO NOT WAIT UNTIL THE LAST MINUTE TO ASK FOR HELP ON ASSIGNMENTS!

Students with Disabilities

I am committed to creating a course that is inclusive in its design. If you encounter barriers,
please let me know immediately so we can determine if there is a design adjustment that can be
made. I am happy to consider creative solutions as long as they do not compromise the intent of
the assessment or learning activity.

If you have a disability, or think you may have a disability, you may also contact the Disability
Services and Programs for Students (DSPS) office or visit their website. If you have already been
approved for accommodations through DSPS, please share with me your letter of
accommodations.

DSPS Office Contact Information

Website: https://flc.losrios.edu/student-resources/support-services/dsps
Phone: (916) 608-6611

Email: [email protected]

Class Completion & Financial Aid

If you are a Financial Aid recipient, please note that unsuccessful completion of this class or
course completion of at least 60% of the semester, may result in repayment of all or part of your
student financial aid. For further information, please contact the Financial Aid Office at (916)
608-6646.

Extra Help

I am here to help you be successful in this course. Please do not hesitate to contact me via the
Canvas Inbox. I will respond to your messages within 48 hours.

Office Hours: I am happy to schedule virtual office hours for ZOOM meetings. My preferred
day for meeting is Friday but can be available other days on a case-by-case basis.

Additionally, an FAQ discussion forum is available where students can post and answer
questions or provide other helpful information. Please adhere to the Netiquette standards when
posting to the forum.

Agility

I reserve the right to change the syllabus at any time for any reason.

Last Update: 2024-10-18

Change Log

Date Changes
2024-10-18 Initial Release