In this course, you will learn the concepts, methods, and applications of computer vision and image processing. You’ll build a foundation that can be used to develop practical applications and provide the basis for more advanced studies. The course begins with vision and image fundamentals, including image formation and display, digital camera and image capture, the human visual system, and visual perception. You will learn the basics of image processing, including spatial and frequency domain filtering techniques and applications and compression algorithms. The course further dives into neural network-based algorithms, such as CNN and Vision Transformers. The course covers practical image analysis and inference methods, including edge, contour, feature detection, image segmentation, matching, and stitching, as well as object and facial recognition. Additional discussions will cover the development of 3D computer vision, real-time human-computer interaction, emerging technologies, applications, and trends.

We will use Python and TensorFlow to develop these apps. Numerous well-illustrated examples and engaging hands-on projects will be used to demonstrate these principles in practical real-world computer vision applications.

Learning Outcomes
At the conclusion of the course, you should be able to

• Explain the concepts of Computer Vision
• Discuss the computer vision applications, use cases, and challenges across industries and real-world problems
• Compare traditional and neural-network-based imaging algorithms for their strengths and weaknesses
• Apply neural-network-based imaging algorithms and techniques

Topics Include

• Image formation, image understanding, pattern matching, geometry understanding, and synthesis
• Image denoising, object detection, image superresolution, and image segmentation