EEL 6562 -- Image Processing and Computer Vision

University of Florida

Department of Electrical and Computer Engineering

EEL 6562, Section 8422

Image Processing and Computer Vision

Fall 2007

Course Description

This course introduces fundamental concepts and techniques for image processing and computer vision. We will address 1) how to efficiently represent and process image/video signals, and 2) how to deliver image/video signals over networks. Topics to be covered include: image acquisition and display using digital devices, properties of human visual perception, sampling and quantization, image enhancement, image restoration, two-dimensional Fourier transforms, linear and nonlinear filtering, morphological operations, noise removal, image deblurring, edge detection, image registration and geometric transformation, image/video compression, video communication standards, video transport over the Internet and wireless networks, object recognition and image understanding.

Course Prerequisites

EEL 3135 (Discrete-Time Signals and Systems) or undergraduate-level signals and systems
EEL 4516 (Noise in Devices and communication Systems) or undergraduate-level probability theory/stochastic processes
Some exposure to MATLAB and C programming language
Knowledge of basic matrix theory (linear algebra) would be helpful, but not necessary

Textbook

Rafael C. Gonzalez, Richard E. Woods, ``Digital Image Processing,'' 3rd Edition, Prentice Hall; ISBN: 013168728X; August 2007.

Rafael C. Gonzalez, Richard E. Woods, ``Digital Image Processing,'' 2nd Edition, Prentice Hall; ISBN: 0201180758; January 15, 2002.

Instructor:

Dr. Dapeng Wu
Office: NEB 431
Email: wu@ece.ufl.edu

TA:

Xiaochen Li
Email: lxc@ufl.edu

Course website: http://www.wu.ece.ufl.edu/courses/eel6562f07

Meeting Time

Monday, Wednesday, Friday, period 10 (5:10 pm - 6 pm)

Meeting Room

NEB 101

Office Hours

Dr. Wu: Monday, period 9 (4:05 pm-4:55 pm) & Wednesday, period 9 (4:05 pm-4:55 pm), and by appointment via email.

Structure of the Course

The course consists of lectures, 10 homework assignments, 1 project, and 1 exam.

This course is primarily a lecture course.   I cover all important material in lectures. Since EEL 3135 and EEL 4516 are prerequisites, I assume some previous knowledge about DSP, probability theory and stochastic processes, and hence I will cover some material very quickly. Thus, depending on what and how much you recall from earlier study, varying amounts of reading in introductory books on DSP, probability theory and stochastic processes (other than the course textbook) may be necessary; these readings are up to the student. I will only give reading assignments from the course textbook.

Attending lecture is quite important as I may cover material not available in any book easily accessible to you. I use Powerpoint presentation during lecture. Lecture notes will be posted on the course website before the class. The lecture is to engage the students in independent thinking, critical thinking, and creative thinking, help the students organize the knowledge around essential concepts and fundamental principles, and develop conditionalized knowledge which tells them when, where and why a certain method is applicable to solving the problem they encounter.

I do not intend for the WWW material to be a substitute for attending lecture since engaging the students in active thinking, making logical connections between the old knowledge and the new knowledge, and providing insights are the objectives of my lecture.   The lecture notes are posted on the web so that you can miss an occasional lecture and still catch up, and it makes taking notes easier. To reward those who attend regularly, there will be some lecture-based material in the exam which is not available via the web.

Some problems in the exam will be similar to those in the homework.   As long as you work out the homework by yourself, you will be successful in the exam.   The problems in the exam are designed to prevent the students from memorizing the homework solutions without understanding the fundamental principles, concepts, and theories.   So, to prepare the exam, the first thing is to understand the material; then use the homework problems to test your understanding.

The class project is described here.

Course Outline

Overview of image processing systems, Image formation and perception, Continuous and digital image representation
Image quantization: uniform and nonuniform, visual quantization (dithering).
Image contrast enhancement: linear and non-linear stretching, histogram equalization.
Continuous and discrete-time Fourier Transforms in 2D; and linear convolution in 2D.
Image smoothing and image sharpening by spatial domain linear filtering; Edge detection.
Discrete Fourier transform in 1D and 2D, and image filtering in the DFT domain.
Median filtering and Morphological filtering.
Color representation and display; true and pseudo color image processing.
Image sampling and sampling rate conversion (resize).
Lossless image compression: The concept of entropy and Huffman coding; Runlength coding for bi-level images; CCITT facsimile compression standards.
Lossy image compression: Image quantization revisited; Predictive coding; Transform coding; JPEG image compression standard.
Imaging Geometry; Coordinate transformation and geometric warping for image registration.
Object recognition

Course Objectives

Upon the completion of the course, the student should be able to

know the fundamental techniques for image processing, video processing, and computer vision
understand the basics of analog and digital video: video representation and transmission
acquire the basic skill of designing image/video compression
familiarize himself/herself with image/video compression standards

Handouts

Please find handouts here.

Course Policies

Attendance:
- Perfect class attendance is not required, but regular attendance is expected.
- It is the student's responsibility to independently obtain any missed material (including handouts) from lecture.
- There will be no make-up exams.
During lecture, cell phones should be turned off.
No late assignment
Announcements:
- All students are responsible for announcements made in lecture, on the student access website, or via the class email list.
- It is expected that you will check your email several times per week for possible course announcements.
Students with disabilities:
- Student requesting classroom accommodation must first register with the Dean of Students Office. The Dean of Students Office will provide documentation to the student who must then provide this documentation to the Instructor when requesting accommodation. For more information on classroom accommodation, please click here.
Intellectual Integrity

All students admitted to the University of Florida have signed a statement of academic honesty committing them to be honest in all academic work and understanding that failure to comply with this commitment will result in disciplinary action. This statement is a reminder to uphold your obligation as a student at the University of Florida, and to be honest in all work submitted and exams taken in this class and all others. Refer to the academic honor code for more information.

Students are encouraged to discuss class material in order to better understand concepts. All homework answers must be the author's own work. However, students are encouraged to discuss homework to promote better understanding. What this means in practice is that students are welcome to discuss problems and solution approaches, and in fact can communally work solutions at a board. However, the material handed in must be prepared starting with a clean sheet of paper (and the author's recollection of any solution session), but not refer to any written notes or existing code from other students during the writing of the solution. In other words, writing the homework report shall be an exercise in demonstrating the student understands the materials on his/her own, whether or not help was provided in attaining that understanding.

Useful links:

For university counseling services and mental health services, please click here.

Grading:

Grades	Percentage	Dates
Homework	40%	See the course calendar
Final exam	30%	Dec. 12
Project proposal	5%	Oct. 24
Project report	25%	Dec. 12

Homework:

There are 10 assignments. Due dates of assignments are specified in the course calendar.
No late submissions are allowed. The highest six homework grades will be chosen in the calculation of final grade. Solutions provided by the instructor will be handed out in the next class after the homework is due.
If you wish to dispute a homework grade, you must return the assignment along with a succinct written argument within one week after the graded materials have been returned to the class. Simple arithmetic errors in adding up grade totals are an exception, and can normally be handled verbally on-the-spot during office hours of the TA. For all other disputes, the entire homework may be (non-maliciously) re-graded, which may result in increase or decrease of points.

Class Project:

The class project will be done in a group of at most four members (that is, 1 or 2 or 3 or 4 members are allowed). Each project requires a proposal and a final report. The final report is expected to be in the format of a conference paper. On Oct. 24, the project proposal (up to 2 pages) is due. On Dec. 12, the final report (up to 10 pages) is due. For details about the project, please read here.

Suggested topics for projects are listed here.

Course calendar can be found here.

Related courses in other schools:

George Mason University, Computer Vision

Johns Hopkins University, Image Compression and Packet Video

Polytechnic University, Video Processing

Purdue University, Digital Video Systems

Stanford University, Digital Video Processing

University of California, Berkeley, Multimedia Signal Processing, Communications and Networking

University of Maryland, College Park, Digital Image Processing

University of Maryland, College Park, Multimedia Communication & Information Security: A Signal Processing Perspective

Useful links

Introduction to Matarix Algebra (free book by Autar K Kaw, Professor, University of South Florida).
Matrix Reference Manual
Matlab Primer, Matlab Manuals, Image Processing Toolbox
HIPR2: a WWW-based Image Processing Teaching Materials with J
Matlab implementation of image/video compression algorithms
LIDAR

Standards:

H.264 tutorial
H.263
MPEG4 overview can be found at http://www.chiariglione.org/mpeg/standards/mpeg-4/mpeg-4.htm

ATSC (Advanced Television Systems Committee) & HDTV (High Definition Television):

ATSC.org

HDTV

SMPTE.org

MPEG (Moving Picture Experts Group):

MPEG.org

MPEG standards committee

MPEG TV

MP3

MPEG Audio Layer-3

Software:

Video codec
ImageJ: Read and write GIF, JPEG, and ASCII. Read BMP, DICOM, and FITS. [Open Source, Public Domain]
Open source for image processing tasks: http://octave.sourceforge.net/doc/image.html
Photosynth: you can access gigabytes of photos in seconds, view a scene from nearly any angle, find similar photos with a single click, and zoom in to make the smallest detail as big as your monitor.
- Refer to: http://labs.live.com/photosynth/
- A demo video: http://www.ted.com/index.php/talks/view/id/129

HSI color model

Compression link: http://cchen1.et.ntust.edu.tw/compression/compression.htm

JOURNALS

Elsevier

Computer Vision and Image Understanding
Digital Signal Processing: A Review Journal
Graphical Models and Image Processing
Journal of Visual Commuication and Image Representation
Real-Time Imaging
Computers & Graphics
Data & Knowledge Engineering
Image and Vision Computing
Pattern Recognition
Pattern Recognition Letters
Signal Processing
Signal Processing: Image Communication

IEEE

IEEE Transactions on Circuits and Systems for Video Technology
IEEE Transactions on Multimedia
IEEE Transactions on Image Processing
IEEE Transactions on Medical Imaging
IEEE Transactions on PAMI

Kluwer

SPIE

Journal of Electronic Imaging

Digital Video and Multimedia Standards Pages

Digital TV and DVD

Overview of the AVI format

Signal Processing Information Base (SPIB)

Computer Vision

Computer Vision Homepage at CMU
Annotated Computer Vision Bibliography from USC IRIS
CVonline: The Evolving, Distributed, Non-Proprietary, On-Line Compendium of Computer Vision
3-D for Everyone
Red-blue glasses or anaglyph for 3D viewing: http://www.best3dglasses.com/anaglyph.html
Shutter glasses for 3D viewing: http://www.stereo3d.com/shutter.htm
3D cameras: http://www.ptgrey.com/index.asp
3D photos at http://www.jessemazer.com/3Dphotos.html

Public Domain Image Databases

CMU Database

Patent licensing

As with MPEG-2 Parts 1 and 2 and MPEG-4 Part 2 amongst others, the vendors of H.264/AVC products and services are expected to pay patent licensing royalties for the patented technology that their products use. The primary source of licenses for patents applying to this standard is a private organization known as MPEG-LA, LLC (which is not affiliated in any way with the MPEG standardization organization, but which also administers patent pools for MPEG-2 Part 1 Systems, MPEG-2 Part 2 Video, MPEG-4 Part 2 Video, and other technologies).

To search patents, visit free patent searching site: www.FreePatentsOnline.com.