Computer Vision

This course provides the introduction to the fundamental computer vision, and image processing techniques. Topics covered in detail includes camera geometry, image formation, image filtering, thresholding and image segmentation, edge, point and line detection, feature base alignment, pose estimation, object detection, face recognition and scene understanding. The focus of the course is to learn the methods, algorithm and theory use in computer vision and then practice in the projects.

Upon the successful completion of this course, students should be able to:

• Demonstrate the thorough understanding of fundamental theories and techniques in the field of image processing and computer vision.
• Experiment with the image filtering techniques, multi-scale representation, edge detection, segmentation and detection of other primitives and object recognition.
• Analyze and evaluate the strengths and weaknesses of different methods and algorithms for solving existing computer vision problems.
• Apply the methods, and techniques for creating computer vision related applications.

Textbook:

1. Computer Vision: Algorithms and Applications” by Richard Szeliski

References: 

1. “Fundamentals of Computer Vision” by WESLEY E. SNYDER North Carolina State University
2. “Computer Vision A Modern Approach”, by Forsyth-Ponce