Course Description
This course provides an introduction to the fundamentals of computer vision and image processing, designed to equip students with the essential knowledge and practical skills for building real-world applications. Students will learn to use OpenCV for image and video analysis, Keras for constructing and training deep learning models, and Intel's OpenVINO toolkit for optimizing and deploying these models for high-performance inference. The overarching focus is on bridging theory with practice, ensuring that upon completion, students can create a complete computer vision application, from initial data processing to final, optimized deployment. (3 credits)
Prerequisite
- ITE 301: Introduction to AI and Generative AI
Student Learning Outcomes (SLOs)
Students who successfully complete this course will be able to:
- Describe computer vision and its evolution over time.
- Explore the applications of computer vision and its societal impact.
- Explain the mathematical concepts used in various computer vision applications.
- Analyze the steps involved in executing a computer vision project starting from data acquisition followed by necessary preprocessing steps.
- Describe the building blocks of Convolutional Neural Networks, the activation functions, and their importance.
- Explore the effects of hyperparameter tuning in Convolutional Neural Networks.
- Analyze the principles and mechanisms of transfer learning.
- Explore Python libraries such as OpenCV, TensorFlow, and Keras, and demonstrate their use in various computer vision applications through hands-on implementation.
- Develop and implement a computer vision project utilizing You Only Look Once (YOLO) and Generative Adversarial Network (GAN) models.
- Evaluate ethical considerations behind using Generative Adversarial Networks.
- Design and implement a hands-on project using OpenVINO pre-trained models.
- Discuss and interpret the future of computer vision based on current and upcoming trends.
Course Activities and Grading
| Assignments | Weight |
|---|---|
Discussions (Weeks 1-8) | 16% |
Quizzes (Weeks 1-7) | 14% |
Assignments (Weeks 1-8) | 70% |
Total | 100% |
Required Textbook
This course uses Open Educational Resources (OER). OER are openly licensed, educational resources that can be used for teaching, learning and research. OER may consist of a variety of resources such as textbooks, videos and software that are no cost for students.
Course Schedule
Week | SLOs | Readings and Exercises | Assignments |
1 | 1,2,3 | Topic: Introduction to Computer Vision and Mathematics for Computer Vision |
|
2 | 4 | Topic: Data Acquisition and Exploration |
|
3 | 4,5 | Topic: Data Exploration and Introduction to CNN |
|
4 | 5,6,7 | Topic: Building Blocks of CNN and Transfer Learning |
|
5 | 8,9 | Topic: Hands-on with OpenCV and YOLO |
|
6 | 8,9,10 | Topics: Tensorflow, Keras and Generative Adversarial Network |
|
7 | 11 | Topic: OpenVINO and Explainable AI |
|
8 | 12 | Topic: Deploying Computer Vision Applications |
|
COSC Accessibility Statement
Charter Oak State College encourages students with disabilities, including non-visible disabilities such as chronic diseases, learning disabilities, head injury, attention deficit/hyperactive disorder, or psychiatric disabilities, to discuss appropriate accommodations with the Office of Accessibility Services at OAS@charteroak.edu.
COSC Policies, Course Policies, Academic Support Services and Resources
Students are responsible for knowing all Charter Oak State College (COSC) institutional policies, course-specific policies, procedures, and available academic support services and resources. Please see COSC Policies for COSC institutional policies, and see also specific policies related to this course. See COSC Resources for information regarding available academic support services and resources.