Computer Vision and Image Processing

Course Overview

This course provides a comprehensive foundation in digital image processing and computer vision. It covers both classical techniques and modern deep learning approaches used in visual computing systems. Students gain hands-on experience using tools such as OpenCV and deep learning frameworks to solve real-world problems in domains like healthcare, automation, and robotics.

By the end of this course, students will be able to:

• Understand image formation, representation, and human vision principles
• Apply image processing techniques such as filtering, segmentation, and feature extraction
• Develop computer vision solutions using modern libraries like OpenCV and PyTorch/TensorFlow

Prerequisites

• No formal prerequisites
• Basic programming knowledge (preferably Python) is recommended

Textbooks

• Primary: Digital Image Processing by Rafael C. Gonzalez and Richard E. Woods (4th Edition, 2018)
• Reference 1: Computer Vision: Algorithms and Applications by Richard Szeliski (2nd Edition, 2022)
• Reference 2: Foundations of Computer Vision by Torralba, Isola, and Freeman (2010)

Grading

• Mid-Term Exam: 25%
• Class Tests: 10%
• Final Exam: 50%
• Assignment / Project: 10%
• Class Participation / Attendance: 5%

Course Outcomes

• CO1: Explain image formation techniques, human vision principles, and digital image representation
• CO2: Apply image processing methods to solve computer vision problems
• CO3: Implement and evaluate computer vision systems using modern frameworks

Teaching and Assessment Strategy

• Lectures with interactive discussions
• Hands-on coding sessions and demonstrations
• Practice problems and quizzes
• Assignments and project-based learning
• Written examinations

Schedule

Week	Date	Topic	Materials
1		Introduction to Computer Vision and Digital Images Overview of course, applications of computer vision and image processing, and fundamentals of digital image representation.
2		Human Vision and Image Formation Human eye mechanism, image acquisition, sampling and quantization, and color models.
3		Spatial Domain Processing Point operations, histogram processing, and arithmetic/logical image operations.
4		Thresholding and Morphological Operations Global and adaptive thresholding, Otsu’s method, and binary morphology techniques.
5		Edge Detection and Filtering Edge detection operators, smoothing, sharpening, and frequency domain filters.
6		Noise Models and Image Segmentation Noise types, filtering techniques, and segmentation methods including region-based approaches.
7		Image Compression JPEG encoding, Huffman coding, and compression techniques.
8		Feature Detection and Matching Feature descriptors, Harris corner detection, and image resampling.
9		Image Transformations and Stereo Vision Affine transformations, image alignment, and stereo/multiview vision concepts.
10		Machine Learning for Vision Basics of classifiers, nearest neighbors, linear classification, and loss functions.
11		Deep Learning for Computer Vision Neural networks, CNNs, and support vector machines.
12		Advanced Vision Models and Applications CNNs, Vision Transformers, YOLO object detection, and course review.