CS 790Q
 Biometrics

The main objective of the course is to introduce you to the area of Biometrics. Biometrics refers to the identification of an individual based on his/her physiological characteristics, like a fingerprint, face, voice or behavior like handwriting or keystroke patterns. Because biometric characteristics are unique to each individual, they can be used to prevent theft of fraud. In addition, unlike a password or a PIN, a biometric cannot be lost, stolen, or recreated. This course is primarily intended for **highly motivated** students who are interested in working on the area of Biometrics. There are many problems in this area suitable for investigation by graduate students leading to a master thesis or dissertation.


EE
484/684  Digital Signal Processing

Discrete signals and systems, the Z transform, digital filter design
techniques, the Fast Fourier Transform, modeling, analysis, and simulation
of discrete random signals and systems.


CS
474/674  Image Processing and Interpretation

Image files, thresholding, histogram transformation, spectra, connectedness, edges, filtering, detection and recognition of objects, optical character recognition.


CS
485/685  Computer Vision

Principles, design and implementation of visionbased systems. Camera models and
image formation, feature detection, segmentation. Camera calibration, 3D
reconstruction, stereo vision. Introduction to advanced topics.


CS
486/686  Advanced Computer Vision

Projective geometry, 3D reconstruction from multiple views. Motion analysis and
tracking. Object, face and gesture recognition, biometrics, humancomputer
interaction. Image and video understanding.


CS
491Y/791Y  Mathematical Methods for Computer Vision

Computer Vision is a broadbased field of computer science that requires
students to understand and integrate knowledge from numerous disciplines.
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. 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.


CS
773  Machine Intelligence

(a) Intelligent systems, (b) neural computing, (c) advanced applications. Selforganizing, selfadapting systems; cybernetics; neural networks; automated decision making and control; learning automata; expert systems application; knowledge and data engineering; pattern recognition, image processing.


CS
790Q  Machine Learning

Supervised and selforganizing learning systems, feature processing, clustering as selforganization, agglomerative versus decisive processes, components of a pattern recognition (PR) system, feature vectors, competitive learning, fuzzy competitive learning, Bayesian classification and linear discrimination, weighting features, nonEuclidean distances between feature vectors, kmeans clustering (Forgy versus MacQueen), improved kmeans clustering, fuzzy cmeans clustering, other fuzzy clustering, fuzzy merging of clusters, clustering validity measures, graphical methods for forming clusters, radial basis function neural networks for supervised learning, automata and recognizers, data mining via clustering: discovering rules in data.


CS
491S/791S  Neural Networks

Neural networks provide a model of computation drastically different from
traditional computers. Typically, neural networks are not explicitly
programmed to perform a given task; rather, they learn to do the task from
examples of desired input/output behavior. The networks automatically
generalize their processing knowledge into previously unseen situations,
and they perform well even when the input is noisy, incomplete or
inaccurate. These properties are wellsuited for modeling tasks in
illstructured domains such as face recognition, speech recognition and
motor control.
This course covers basic neural network architectures and learning
algorithms, for applications in pattern recognition, image processing, and
computer vision. Three forms of learning will be introduced (i.e.,
supervised, unsupervised and reinforcement learning) and applications of
these are discussed. Students have a chance to try out
several of these models on practical problems.


CS
480/680  Computer Graphics

Software, hardware and mathematical tools for the representation, manipulation and display of two and threedimensional objects: applications of these tools to specific problems.


CS
479/679  Pattern Recognition

Pattern recognition systems, statistical methods, discrimination functions, clustering analysis, unsupervised learning, feature extraction and feature processing.


CS
476/676  Artificial Intelligence

Problem solving, search, and game trees. Knowledge representation, inference, and rulebased systems. Semantic networks, frames, and planning. Introduction to machine learning, neuralnets, and genetic algorithms.


CS/Math
483/683  Numerical Methods I

Numerical solution of linear systems, including linear programming; iterative solutions of nonlinear equations; computation of eigenvectors, matrix diagonalization.


CS/Math
484/684  Numerical Methods II

Numerical differentiation and integration; numerical solution of ordinary differential equations, two point boundary value problems; difference methods for partial differential equations.

