Computer Science Department

CS4/791Y: Mathematical Methods for Computer Vision (Fall 2003)

  • Meets: TR: 2:30 - 3:45pm (MS 227)
  • Instructor: Dr. George Bebis

  • Texts:

    Related UNR Courses

  • Computer Vision resources

    Useful links to Neural Networks and Genetic Algorithms resources

    Useful links to Pattern Recognition resources

    Useful links on Algorithms resources

    Useful Mathematics, Statistics, and Geometry resources

    Course Description

    Computer Vision is a broad-based field of computer science that requires students to understand and integrate knowledge from numerous disciplines such as Image Processing, Computer Graphics, Pattern Recognition, Machine Learning, Neural Networks, Genetic Algoritnms, Fuzzy Logic, and Artificial Intelligence. Students are expected to strong background in calculus, linear algebra, probabilities, statistics, geometry, and algorithms. Scientists engaged in this field inevitably have to learn many things about a discipline in which they did not receive formal training. Computer science and electrical engineering majors, however, do not necessarily have an interdisciplinary background. In an effort to makeup for students' weak background, many instructors either spend too much time on teaching background concepts or just skip the mathematical details and proceed immediately to demos and implementation. The purpose of this course is to help bridge the gap for more students to do research in computer vision by teaching them some of the most important and essential mathematical tools used in computer vision research. Our goal is to emphasize those mathematical techniques which have been extensively evaluated and demonstrated to be useful in practical applications. Our emphasis will be on the application aspect of these mathematical techniques in computer vision. We will try to cover at least one technique each week. Once we have discussed the necessary mathematical details, we will concentrate on discussing applications.

    Course Policies

    Exams/Quizzes: there will be no exams but there will be short quizzes every time we finish a topic.

    Course Project: there will a course project which should be done on an individual basis. Specific project ideas will be discsused in class. You will be using C++ or Matlab. You will be required to turn in regular progress reports and a final report which should include a description of the problem, a description of your approach, and your evaluation of the results. You will be also required to do a presentation of your project work at the end of the semester.

    Presentations: each student is required to present a few papers to the rest of the class. The presentations should be professional as if it was presented in a formal conference (i.e., slides/projector).

    Course Prerequisites

    Calculus I-III, Probabilities and Statistics, Data Structures and basic knowledge of image manipulation. Background on Linear Algebra will be very useful. Courses on image processing, computer vision, pattern recognition, machine learning, neural networks, artificial intelligence, and genetic algorithms are recommended, but not required. Good programming skills are essential.

    Matlab Resources

    Ghostview(software for viewing postscript files)
    ResearchIndex (a scientific literature digital library - find papers easy !)


    Course Project

    Course Material

    Programming Assignments