VRL an eye

Courses

ECE 158. Digital Signal Processing

Prof. Mitra

Prerequisites: ECE 130A-B, or consent of instructor. Mathematics 124A is recommended but not required.

Open to ECE majors only. Lecture, 3 hours; laboratory, 3 hours. Discrete signals and systems, convolution, z-transforms, discrete Fourier transforms, digital filters. (F)

ECE 160. Multimedia Computing

Prof. Manjunath

Prerequisites: ECE 155A, 158, and 178. Not open for credit to students who have completed Computer Science 182.

Lecture, 3 hours; laboratory, 3 hours. Introduction to multimedia and applications, including video conferencing, WWW, digital libraries, video on demand. Digital video and audio communication architectures, standards (including JPEG and MPEG2), multimedia storage and retrieval. Multimedia computing on the Internet and digital libraries. (not offered 1999-2000)

ECE 178. Fundamentals of Computer Image Processing

Prof. Manjunath

Prerequisites: ECE 15 and ECE 130A-B, or consent of instructor. Open to ECE majors only.

Lecture, 3 hours; discussion, 1 hour. Basic concepts in image processing. Techniques, capabilities, and limitations with emphasis on use of digital computer but also of optical and analog systems. Image sampling, reconstruction, enhancement, restoration, data extraction, and coding. Some hands-on laboratory experience is offered. (W) more...

ECE 181B. Introduction to Computer Vision

Prof. Manjunath

Same course as Computer Science 181B. Lecture, 3 hours; discussion, 1 hour.

Overview of image processing, pattern recognition; image formation, binary images; edge detection, image segmentation, introduction to textured image analysis, optical flow, depth from stereo, shape from shading, shape from motion, shape representation techniques, issues in object recognition, case study of some vision systems.(S) more...

ECE 258A. Advanced Digital Signal Processing

Prof. Mitra

Prerequisite: ECE 158 or consent of instructor. Lecture, 4 hours.

Digital filter design, discrete random signals, effects of finite word length arithmetic, fast Fourier transform and applications, power spectrum estimation. (W)

ECE 258B. Multirate Digital Signal Processing

Prof. Mitra

Prerequisites: ECE 158 and ECE 258A or consent of instructor. Lecture, 4 hours.

Multirate digital filter theory, polyphase decomposition, decimator and interpolar design, efficient implementations, orthogonal transforms, wavelet transform, analysis and synthesis filter banks, quadrature mirror filter banks, transmultiplexer, subhand decomposition, applications. (S)

ECE 277A. Neural Network Theory

Prof. Manjunath

ECE 278A. Digital Image Processing

Prof. Manjunath

Prerequisites: ECE 158 or equivalent, ECE 178, or consent of instructor. Lecture, 3 hours; laboratory, 3 hours.

Two-dimensional signals and systems. Two-dimensional Fourier and z-transforms. Discrete Fourier transform, two-dimensional digital filters. Image processing basics, image enhancement and restoration. Special image processing software available for laboratory experimentation. (S)

ECE 281B. Advanced Topics in Computer Vision

Prof. Manjunath

Prerequisite: ECE 181B, or consent of instructor. Lecture, 3 hours; Same course as Computer Science 281B.

Advanced topics in computer vision: image sequence analysis, spatio temporal filtering, camera calibration and hand-eye coordination, robot navigation, shape representation, physically-based modeling, multi-sensory fusion, biological models, expert vision systems, and other topics selected from recent research papers. (F; offered alternate years) more...

ECE 594N. Introduction to Data Mining

Prof. Manjunath

Recommended Text: Principles of Data Mining by Hand, Mannila and Smith, MIT Press, 2001.

Data mining refers to tools and techniques for processing and managing large collections of data with the main objective being able to detect significant "patterns" or associations in such data sets. As such, it has a wide range of applications to problems in natural and social sciences, medicine, finance, and marketing. This introductory course will cover some of the basic principles of data mining with emphasis on data mining tasks and algorithms. These will include, for example, tools for classification and clustering, data structures for organizing high-dimensional data, association rules for mining, and retrieval by content (mostly chapters 9-14 in the recommended text above, but I will also be using other resources.)