Lib4U

‎"Behind every stack of books there is a flood of knowledge."

EE 264: Image Processing and Reconstruction

MDSP_Logo

Fundamental concepts in digital image processing and reconstruction. Continuous and discrete images, image acquisition, sampling. Linear transformations of images, convolution and superposition. Image enhancement and restoration, spatial and spectral filtering. Temporal image processing: change detection, image registration, motion estimation. Image reconstruction from incomplete data. Applications.

Instructor: Peyman Milanfar
Office: Engineering 2 , Room 243A
Phone: (831) 459-4929
email: milanfar@ee.ucsc.edu
Lecture: T/Th 10:00 to 11:45, Baskin 156
Office Hours: T/Th 1-2 PM or by appointment
Required Text: Digital Image Processing by Gonzalez and Woods, Third Edition (Errata)
Optional Reference Texts:
  • Digital Image Processing Using MATLAB by Rafael C. Gonzalez, Richard E. Woods, Steven L. Eddins
  • Digital Image Processing by William K. Pratt
  • Fundamentals of Digital Image Processing by Anil K. Jain
  • Two-Dimensional Imaging by Ronald N. Bracewell
Grading Policy: Homeworks (20%), Midterm (30%), Final Project (50%)
Notes on MATLAB: Homework exercises will require the use of the software package MATLAB. Here are some resources to get you started:

 

 

 

Important Dates:

First day of class Thursday, Sept. 22
Last day of class Thursday, December 1
Midterm examination Tuesday, November 8
Final Project presentations Tuesday, December 6
Final Project reports, presentation slides, and code due Tuesday, December 6

 

Lecture Notes:

  1. Overview
  2. Review
    1. Matrix Identities
  3. Image Formation, Sampling, and Resolution
    1. The Myth of Megapixels (NY Times article by David Pogue)
  4. Point-wise Operations
    1. Retinex
    2. Histogram Equalization Derivation
    3. Optimal Averaging Derivation
  5. Local Operations in the Image Domain
  6. 2-D Signals and Systems, Matrix Formulations
  7. The Frequency Domain
  8. Filtering in the Freq. Domain, Sampling.
  9. Some additional notes on the frequency domain
  10. Restoration I: Description and basics of freq. domain approach
  11. Restoration II: Power Spectra and the Wiener Filter
  12. Restoration III: Basics of Pixel-domain Restoration and Statistical Methods
    1. The SVD and SVD-based regularization
    2. ML/MAP and Weighted MAP
  13. Restoration IV: Advanced Pixel Domain Restoration, Implementation
  14. Midterm Review Notes
    1. Previous Year’s Midterm (Solutions)
  15. Motion Estimation I: Intro, models and block-based matching
  16. Motion Estimation II: Optical Flow motion estimation
  17. Multiresolution Image Processing
  18. Introduction to Compression
    1. Video Coding
  19. Indirect Imaging: Tomography
  20. Introduction to Image Analysis
  21. Color Imaging
  22. Kernel and Nonlinear Filtering Methods
 

 

 

  • Lecture Recordings are on iTunes

 Homeworks:

Term Project:

  • Projects will be on a topic from the list (link below), with my approval
    • Project teams of at most 2 students
      • SELECT YOUR PROJECT ASAP, but no later than the midterm date. Only one team will be able to work on each project topic.
  • Project deliverables:
    • Written report approximately 15 pages long. PDF format. (Example)
    • 15-20 minute oral presentation. PPT/PDF format. (Example)
    • Implementation of project ideas in computer code: MATLAB format in Zip Archive. (Example)
  • Final Projects Page (UPDATED WITH REQUIRED PROJECT SUMMARY DESCRIPTION)

Links and Matlab Demos:

Tentative Syllabus and Reading:

  • Week 1 (Ch. 1)Introduction, overview of history and applications of Image Processing. Review of the requisite mathematical concepts, including concepts in matrix, probability, and statistical analysis.
  • Weeks 2 (Ch. 2)Fundamentals of Image Processing. Visual Perception, light and the EM spectrum. Image sensing and acquisition. Sampling and quantization.
  • Weeks 3/4 (Ch. 3)Spatial domain image enhancement. Gray-level transforms, histogram procesing, averaging and subtraction of images. Retinex. Spatial Filtering: Convolution and superposition. Smoothing/sharpening filters.
  • Week 5 (Ch. 4)Spectral domain enhancement. Linear transformations of images. Fourier, DCT, etc. Smoothing/sharpening filters. Homomorphic filtering.
  • Week 6/7 (Ch. 5)Image Restoration. Modeling the degradation process. Noise and interfering patterns. Linear, space-invariant degradations. Blind restoration/estimation of the degradation process. Inverse filtering. Wiener filter, Least-squares filter. Geometric transfromations.
  • Week 7 (Ch. 7)Wavelets and Multiresolution processing. Image pyramids, Continuous and discrete wavelet transforms. Wavelets in 2 dimensions. Applications to compression, enhancement, restoration.
  • Week 8 (Ch. 9/10)Basic Image Analysis. Detection of discontinuities and change in images, segmentation and thresholding. Basic morphological processing. Description and respresentation of shape.
  • Week 9 (Notes)Advanced Topics. Multiple-image processing. Image registration. Motion estimation. Resolution enhancement. Inverse Problems in imaging.
  • Week 10 (Notes)Review of material, presentation of final projects.

     

EE 262: Statistical Signal Processing
Covers fundamental approaches to designing optimal estimators and detectors of deterministic and random parameters and processes in noise; includes analysis of their performance. Binary hypothesis testing: the Neyman-Pearson Theorem. Receiver operating characteristics. Deterministic versus random signals. Detection with unknown parameters. Optimal estimation of the unknown parameters: least square, maximum likelihood, Bayesian estimation. Reviews the fundamental mathematical and statistical techniques employed. Many applications of the techniques are presented throughout the course.
EE 264: Image Processing and Reconstruction
Fundamental concepts in digital image processing and reconstruction. Continuous and discrete images, image acquisition, sampling. Linear transformations of images, convolution and superposition. Image enhancement and restoration, spatial and spectral filtering. Temporal image processing: change detection, image registration, motion estimation. Image reconstruction from incomplete data. Applications.
EE 153: Digital Signal Processing
Introduction to the principles of signal processing, including discrete-time signals and systems, the z-transform, sampling of continuous-time signals, transform analysis of linear time-invariant systems, structures for discrete-time systems, the discrete Fourier transform, computation of the discrete Fourier transform, filter design techniques.
EE 103: Signals and Systems
Characterization and analysis of continuous-time signals and linear systems. Time domain analysis using convolution. Frequency domain analysis using the Fourier series and the Fourier transform. The Laplace transform, transfer functions and block diagrams. Continuous-time filters.

Brief Biography

Updated July 2012

Peyman Milanfar is a Professor of Electrical Engineering (Currently on leave at Google.) He was Associate Dean for research and graduate studies from 2010 to 2012. He received the B.S. in EE/Mathematics from Berkeley, and his Ph.D. in EECS from MIT. Prior to UCSC, he was at SRI, and a Consulting Professor of CS at Stanford. In 2005 he founded MotionDSP , which has brought state-of-art video enhancement to market. His interests are in statistical signal, image and video processing, computational photography and vision. He is a member of the IEEE Signal Processing Society’s IVMSP Technical Committee, and its Awards Board. He is a Fellow of the IEEE.

Source:

http://classes.soe.ucsc.edu/ee264/Fall11/

http://classes.soe.ucsc.edu/ee264/

http://users.soe.ucsc.edu/~milanfar/teaching/index.html

http://users.soe.ucsc.edu/~milanfar/

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

Virtual Fashion Technology

Virtual Fashion Education

toitocuaanhem

"chúng tôi chỉ là tôi tớ của anh em, vì Đức Kitô" (2Cr 4,5b)

VentureBeat

News About Tech, Money and Innovation

digitalerr0r

Modern art using the GPU

Theme Showcase

Find the perfect theme for your blog.

lsuvietnam

Learn to Learn

Gocomay's Blog

Con tằm đến thác vẫn còn vương tơ

Toán cho Vật lý

Khoa Vật lý, Đại học Sư phạm Tp.HCM - ĐT :(08)-38352020 - 109

Maths 4 Physics & more...

Blog Toán Cao Cấp (M4Ps)

Bucket List Publications

Indulge- Travel, Adventure, & New Experiences

Lib4U

‎"Behind every stack of books there is a flood of knowledge."

The WordPress.com Blog

The latest news on WordPress.com and the WordPress community.

%d bloggers like this: