Computer Vision — Fall 2026

Course Overview
| Course Code | CSCI/EENG/ROBO 437/507/517 |
| Semester | Fall 2026, August 24 – December 9 |
| Credit Hours | 3 |
| Class Meeting Times | 3:00–4:15 PM, Monday and Wednesday |
| Class Location | CoorsTek 130 |
Prerequisites
- Linear algebra, calculus, probability, and statistics
- Algorithms and Python (or C++). We require you to program in Python.
Course Website: https://ariarobotics.github.io/cv/
Course Repository: https://github.com/ariarobotics/cv
Instructor

Kaveh Fathian
Assistant Professor, Computer Science Department
- Office: Brown 280-N
- Office hours: Monday/Wednesday, 4:15–5:00 PM (after class)
- Lab website: https://www.ariarobotics.com/
Course Description
Computer vision is the process of using computers to acquire images, transform images, and extract symbolic descriptions from images. This course provides an introduction to this field, covering topics in classical computer vision such as image formation, feature extraction, location estimation, and object recognition, as well as modern computer vision techniques based on neural networks, mechanisms for training and running these networks, and their applications in computer vision. Hands-on homework will be assigned to practice popular computer vision software tools.
Learning Objectives
- CLO1. Explain and apply fundamental concepts in image formation, image representation, color, and image processing.
- CLO2. Apply image processing techniques, including filtering, convolution, Fourier-domain analysis, edge detection, and Hough-based methods, to analyze and transform visual data.
- CLO3. Detect, describe, and match visual features using classical computer vision techniques, and apply these features to image analysis and recognition tasks.
- CLO4. Apply principles of camera geometry, camera calibration, two-view geometry, stereo vision, and motion estimation to recover geometric and 3D information from images.
- CLO5. Implement and evaluate classical computer vision methods for recognition and detection, including feature-based approaches such as SIFT and HOG.
- CLO6. Apply machine learning and deep learning methods, including neural networks and convolutional neural networks, to computer vision tasks such as image classification, object detection, and semantic segmentation.
- CLO7. Develop functional computer vision pipelines using tools such as Python and OpenCV, and evaluate their performance on real visual data.
Assessments and Grading
Homework — 60 points
There will be up to 12 homework assignments. Students are allowed to discuss the problems, help each other, use online resources, etc.; however, they must understand the solutions and prepare and submit the homework individually. Identical submissions are considered plagiarism and will receive a grade of zero. Homework solutions will not be posted. Homework submission deadlines will not be extended except in extraordinary circumstances. The maximum score for late homework will decrease by 25% for each week it is late: up to one week late, the maximum score is 75%; up to two weeks late, 50%; up to three weeks late, 25%; and at four weeks late or later, the score is zero. The lowest homework grade, including a missed assignment, will automatically be dropped and will not count toward the final grade. Two or more missed homework assignments will result in an Incomplete grade.
Exams — 40 points
There will be 4 exams scheduled during regular class hours. The exams are based on: lecture slides, class discussions, and homework. Exams will be administered in person, in the classroom. Students who require an alternative testing location or arrangement are responsible for submitting the appropriate requests. Students will not be allowed to use any resources during exams, including lecture notes, online searches, generative AI, calculators, and smartphones. The lowest exam grade, including an absent exam, will automatically be dropped and will not count toward the final grade. No make-up exam will be given for an excused absence except in extraordinary circumstances, as determined at the instructor’s discretion. Documentation must be provided to justify such an exception. Any missed exam will receive a grade of zero. Two or more missed exams will result in an Incomplete grade.
Bonus Points — up to 10 points
At the instructor’s discretion, optional assignments, projects, or other activities may be offered for bonus points. Bonus points are intended to provide students with opportunities to improve their final grade.
Attendance
Attendance is mandatory but will not be monitored. Several course topics will only be discussed in class and added to the slides during the lecture. This material will not be recorded or posted. The instructor is not responsible for correcting attendance-related issues resulting from negligence.
Final Grade
The regular course grade consists of:
| Component | Points |
|---|---|
| Homework | 60 |
| Exams | 40 |
| Total | 100 |
Bonus points are then added to the final grade:
\[ \text{Amended Final Grade} = \text{Final Grade} + \text{Bonus Points} \]
A maximum of 10 bonus points may be added. Any amended grade above 100 points will be capped at 100.
Grading Rubric
| Amended Final Grade | Letter Grade |
|---|---|
| 93–100 | A |
| 90–<93 | A− |
| 87–<90 | B+ |
| 83–<87 | B |
| 80–<83 | B− |
| 77–<80 | C+ |
| 73–<77 | C |
| 70–<73 | C− |
| 67–<70 | D+ |
| 63–<67 | D |
| 60–<63 | D− |
| <60 | F |
Logistics
The primary communication channel between students and the instructor/TAs is the Ed Discussion server, not email or Canvas messaging. The Ed Discussion server is linked through Canvas. All class announcements, questions, and discussions will be posted on Ed Discussion.
Students are expected to have access to a computer, such as a personal laptop, for in-class activities when needed. Smartphones may not be used as a substitute when a computer is required. Workstation computers are available in the classroom. Students may also loan laptops from Mines ITS or the Computer Science Department if needed.
Information about the course TAs and their office hours is available through the course repository: https://github.com/ariarobotics/cv
Resources
There is no required textbook. Lecture slides and other course materials will be provided through the course website: https://ariarobotics.github.io/cv/
Recommended Books
Many of the following are available online.
Computer Vision
- Szeliski, Computer Vision: Algorithms and Applications, Springer, 2010.
- Klette, Concise Computer Vision: An Introduction into Theory and Algorithms, 2014.
- Hartley and Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, 2004.
- Forsyth and Ponce, Computer Vision: A Modern Approach, Prentice Hall, 2002.
- Palmer, Vision Science, MIT Press, 1999.
Learning
- Goodfellow, Bengio, and Courville, Deep Learning, MIT Press, 2016.
- Mitchell, Machine Learning, McGraw-Hill, 1997.
- Duda, Hart, and Stork, Pattern Classification, 2nd Edition, Wiley-Interscience, 2000.
- Sutton and Barto, online book; a classic reference in reinforcement learning.
Graphical Models
- Koller and Friedman, Probabilistic Graphical Models: Principles and Techniques, MIT Press, 2009.
Course Schedule
The detailed class schedule is available on the course website: https://ariarobotics.github.io/cv/. The schedule is subject to change. Exam and homework dates will not change except in extraordinary circumstances.
Policy on Missed Classes, Exams, or Late Assignments
The lowest exam grade, including an absent exam, will automatically be dropped and will not count toward the final grade.
The lowest homework grade, including a missed submission, will automatically be dropped and will not count toward the final grade.
In-person class attendance is mandatory because some material will only be discussed in class and will not necessarily be recorded or posted.
The maximum score for late homework decreases by 25% for each week it is late: up to one week late, the maximum score is 75%; up to two weeks late, 50%; up to three weeks late, 25%; and at four weeks late or later, the score is zero.
Exceptions to the policies above may be granted only under extraordinary circumstances and at the instructor’s discretion. Students must provide appropriate documentation.
Any missed exam will receive a grade of zero before application of the lowest-exam-drop policy.
Two or more missed exams will result in an Incomplete grade.
Two or more missed homework assignments will result in an Incomplete grade.
Other Important Course Policies
Any form of academic dishonesty, misconduct, or plagiarism will be taken very seriously and addressed through the Mines Academic Misconduct process.
No resources are allowed during exams. Use of generative AI tools, such as ChatGPT, is allowed outside of class but is prohibited during class activities where specified, including coding sessions and exams.
Professional language and etiquette are expected from all students. Please report inappropriate conduct or behavior to the instructor.
Mines Policies & Campus Resources
Absences
Mines students are expected to fulfill their academic requirements through attendance and/or participation. Class attendance is required of all students unless the student has an excused absence granted by the school or the student’s professor. It is the student’s responsibility to request an excused absence from the professor or through the established protocol. Excused absences may be issued for unforeseen illness or anticipated and/or authorized medical or personal matters, including religious observance, military commitments, and other qualifying reasons upon review. Exclusions may apply. Opportunistic or habitual abuse of the excused absence policy violates the Mines Code of Conduct. To review the Excused Absence Policy or request an excused absence, visit: https://www.mines.edu/student-life/student-absences/
Sexual Misconduct, Discrimination, and Retaliation
Mines prohibits discrimination and harassment on the basis of age, ancestry, creed, marital status, race, color, ethnicity, religion, national origin, sex (including stalking, dating and domestic violence, non-consensual sexual contact or penetration, sexual exploitation, and sexual harassment), pregnant or parenting status, gender, gender identity, gender expression, disability, sexual orientation, genetic information, veteran status, or military service within any of its education programs or activities, including admissions and employment, or sponsored conferences and events. This prohibition applies to all students, employees, contractors, visitors, including conference attendees, and volunteers. Anyone in the campus community can report or file a complaint of discrimination or sexual misconduct. Please contact OIE@Mines.edu or use the appropriate Discriminatory Harassment and Retaliation Reporting Form. Confidential resources are also available through Mines.
Preferred First Name
Mines recognizes that members of the campus community may prefer to use a first name other than their legal name to identify themselves. Many services on campus, including Canvas, utilize and display preferred first names. Additional information about using a preferred first name is available through the Office for Institutional Equity Preferred First Name resources. Students may also contact the Title IX Coordinator at OIE@Mines.edu.
Pregnant and Parenting Students
If you are a pregnant or parenting student, you have the right to reasonable, non-disability-related modifications. Please contact the Title IX Coordinator in the Office for Institutional Equity at oie@mines.edu for more information or to request support or modifications.
Academic Integrity
Colorado School of Mines affirms the principle that all individuals associated with the Mines academic community have a responsibility for establishing, maintaining, and fostering an understanding and appreciation for academic integrity. Students should review the full academic misconduct and academic integrity policy for definitions of academic misconduct. Resources provided by the Department of Community Standards are also available for guidance regarding academic misconduct and integrity procedures.
Generative Artificial Intelligence
The Office of the Provost encourages the University community to explore the uses and impacts of generative AI technologies through critical discussion and creative applications. Based on the current course policy, the use of generative AI is allowed outside of class but prohibited during class, including coding sessions and exams.
Copyrighted Materials
Readings, lectures, media, data, and software used in this course may be protected by copyright law. You should not post, share, copy, distribute, upload, or publicly display these materials outside of class without permission from the copyright owner. Unauthorized use may result in disciplinary action and legal consequences. Mines copyright policy: https://www.mines.edu/policy-library/copyright-infringement-and-illegal-file-sharing/
Grading Policy
Extra credit may be offered for additional learning activities related to this class. Unless otherwise detailed in this syllabus, the awarding of extra credit is at the discretion of the instructor and is not guaranteed.
Course Issues and Concerns
As part of good professional practice, students are encouraged to speak directly with the faculty member to raise issues and concerns regarding the course professionally and in compliance with the student code of conduct. Students may also contact the course coordinator or the head of the department through which the course is offered. The department head can investigate and work with the faculty member to resolve course-related concerns. Students’ final point of contact is the college dean, who may make final decisions.
Disability Support Services
Disability Support Services (DSS) works collaboratively with students, faculty, and staff to minimize barriers and support an accessible campus community. When barriers to access occur, Disability Support Services works one-on-one with students to determine accommodations and facilitate access to programs and services. If you have been approved for accommodations through Disability Support Services, please contact your professor to confirm receipt of your accommodation letter and discuss implementation of accommodations in this course. For more information or to request accommodations, visit: https://www.mines.edu/disability-support-services/
Digital Accessibility
Colorado School of Mines is committed to supporting an accessible digital environment for all members of the community, including students with disabilities. If you have an accessibility concern with Canvas or any digital materials or software used in this course, please contact your professor or request support from Information Technology. More information: https://www.mines.edu/accessibility/
Student Outreach & Support (SOS) Resources
If you feel overwhelmed, anxious, depressed, or concerned about your overall wellbeing, you can connect with an SOS Case Manager who can help you navigate available resources. If you need assistance, please seek help from a trusted faculty or staff member, a fellow student, or submit a referral for yourself. If you are concerned about another student, you are encouraged to offer assistance and/or seek help on their behalf. More information: https://student-life.mines.edu/student-outreach-and-support/
Student Outreach and Support can help connect students with resources including:
Counseling Center: https://counseling.mines.edu/
Located on the second floor of the Wellness Center, 1770 Elm St.Student Health Center: https://studenthealth.mines.edu/
Located on the first floor of the Wellness Center.SHAPE Office: https://shape.mines.edu/
Provides sexual and interpersonal violence support and is located on the second floor of the Wellness Center.988 Colorado Mental Health Line: Students seeking support for mental health and/or substance-use concerns may call or text 988 or visit https://www.988colorado.com/en.
In an emergency, call 911. Mines or Golden Police Department personnel will be dispatched as appropriate.
Center for Academic Services and Advising (CASA)
CASA provides a variety of academic support services for students during their time at Mines. For a complete list of available academic support services, visit: https://www.mines.edu/casa/academic-support/ Questions may be directed to casa@mines.edu.
Writing Center
The Writing Center is a free academic support service for undergraduate and graduate students. Professional consultants and peer tutors provide support with many forms of communication, including technical and scientific reports, academic essays, and oral presentations. Students may schedule an online or in-person appointment at any stage of a project, from brainstorming through final revisions. More information: https://writing.mines.edu/ Questions may be directed to ryandeanlambert@mines.edu.
Tutoring Resources
The Mines Tutoring page provides information about tutoring locations, hours, and offices appropriate for different academic needs. Visit: https://www.mines.edu/undergraduate-studies/tutoring/