CIS 270 - Artificial Intelligence for Computer Vision

1. Comprehend the foundational principles of computer vision and its integration with AI.
2. Apply various computer vision techniques to analyze and interpret visual data.
3. Implement and evaluate computer vision algorithms for tasks such as image recognition and object detection.
4. Gain proficiency in designing and implementing Convolutional Neural Networks for various computer vision tasks
5. Critically evaluate and analyze contemporary tools and emerging trends in computer vision.
6. Engage in ethical considerations concerning the societal impact of AI in computer vision applications.

Artificial Intelligence in Computer Vision

I. Introduction to Computer Vision and AI (Weeks 1-2)

• a. Overview of computer vision and its relationship to artificial intelligence
• b. Fundamentals of image representation and feature extraction
• c. Introduction to basic computer vision algorithms

II. Deep Learning for Computer Vision (Weeks 3-4)

• a. Understanding deep learning in the context of visual data analysis
• b. Convolutional Neural Networks (CNNs) for image recognition and classification
• c. Practical sessions on implementing CNNs for computer vision tasks

III. Object Detection and Image Segmentation (Weeks 5-6)

• a. Techniques for object detection and localization in images
• b. Image segmentation methods and their applications.
• c. Hands-on exercises on object detection and segmentation algorithms

IV. Video Understanding and Analysis (Weeks 7-8)

• a. Introduction to video data analysis in computer vision
• b. Optical flow, tracking, and action recognition
• c. Project work involving video understanding tasks

V. Ethical Considerations in Computer Vision (Weeks 9-10)

• a. Ethical implications and societal impact of AI in computer vision
• b. Discussion on bias, fairness, and transparency in visual data analysis
• c. Case studies and ethical frameworks in computer vision applications

VI. Advanced Topics in Computer Vision (Weeks 11-12)

• a. Advanced CNN architectures and their optimization techniques
• b. Reviewing contemporary research papers and recent developments
• c. Project-based assignments incorporating advanced computer vision methods

VII. Project Development and Practical Applications (Weeks 13-14)

• a. Independent or group projects focused on real-world applications of computer vision
• b. Guidance and mentorship for project development.
• c. Project refinement and implementation

VIII. Conclusion and Application Showcase (Weeks 15-16)

• a. Finalizing and refining projects for presentation
• b. Presentation of projects to peers, faculty, and industry professionals
• c. Conclusion, reflection on the learning experience, and submission of final project documentation

Facilitated Discussion 20%-30%

Facilitated Group Work 40%-50%

 
English Prerequisite(s): None
Math Prerequisite(s): Eligible for Math 105 or Higher; SAT Math Score of 24.5 or Higher
Course Corerequisite(s): CIS 210 
Course-Specific Placement Test: None
Course Aligned with IRW: NA
Consent to Enroll in Course: No Department Consent Required