Instructor: Dr. Jiang Yu Zheng
Meeting Times: 4:30-5:45pm, TR at SL051
Credits: 3 Cr.
Textbook:
Linda G. Shapiro, George C. Stockman, Computer Vision, Prentice Hall, ISBN
0-13-030796-3
Reference books:
Alan Watt, Fabio Policarpo, The Computer Image, ACM Press, Addison-wesley, ISBN 0-201-42298-0.
Forsyth, Ponce, Computer Vision, A Modern Approach, ISBN 0-13-085798-1
Description: Computer Images are everywhere, occupying a dominant part of the computer culture. Three main fields of computer imagery are computer graphics, image processing and computer vision. Computer vision techniques are used in computer graphics to collect and model complex scenes; computer graphics techniques are used to constrain the recognition of 3D objects by computer; image processing techniques are routinely used by graphic designers to manipulate photographs. This course emphasizes image processing and computer vision, and their merging with many other applications
such as multimedia, virtual reality, and pattern recognition. We
will discuss image input, image transform, feature detection and
recognition in 2D image processing, and stereo, dynamic image, and
3D measure in computer vision. Half of the time will be devoted to
2D image processing and the remaining time will be used to explore
3D world and dynamic images. Students will have significant
programming and problem solving experiences through the course work.
Covered contents:
Image enhancement and basic processing in image space
Edges and their detection
Image transforms
Image segmentation
Image matching
3D Scene understanding
Shape from X
Dynamic images
Moving image in computer vision
Image applications in communication, VR, and multimedia
Evaluation: Term project exploring an unsolved problem, presentation of your project results, exercises (programming) on image processing, discussion and class participation
We will use Oncourse to provide materials and transmit image data.