| Course ID: | CSCI 8820. 4 hours. |
| Course Title: | Computer Vision and Pattern Recognition |
Course
Description: | Low-level and high-level vision including edge detection, connected component labeling, boundary detection, segmentation, stereopsis, motion analysis, and object recognition. Knowledge representation, knowledge retrieval and reasoning techniques in computer vision. Parallel computing, parallel architectures and neural computing for computer vision. |
| Oasis Title: | COMPUTER VISION |
| Prerequisite: | CSCI 4810/6810 or permission of department |
Semester Course
Offered: | Not offered on a regular basis. |
| Grading System: | A-F (Traditional) |
|
| Course Objectives: | The student is expected to develop a clear understanding of the
algorithms and paradigms involved in extracting high-level semantic
information from low-level image data. Although the course is aimed
at computer science students, students in other disciplines that
entail automated analysis of visual/image data would also benefit
from this course. |
| Topical Outline: | Introduction to Computer Vision and Pattern Recognition,
Image processing basics, Region analysis, Edge detection,
Image segmentation, Feature Extraction, Techniques for
extracting 3D shape information from 2D images,
Image texture analysis, Motion analysis, and Object recognition.
In addition to the above topics covered from the textbook, there will be
papers assigned from the current research literature. Students are
also expected to work on a self-directed project either individually
or in a small group. The students are expected to present their
project towards the end of the semester and also submit a technical
report/term paper. |