Department of Computer Science and Engineering
CS474/674 Image Processing and Interpretation (Fall 2019)
Meets: MW 1:00 pm - 2:15 pm (SEM 347)
Instructor:
Dr. George Bebis
- Email:
bebis@cse.unr.edu
- Phone:
(775) 784-6463
- Office: SEM 235
- Office Hours: MW 11:30am - 1pm and/or by appointment
Text:
R. Gonzalez and R. Woods Digital Image Processing, 4th edition, Pearson, 2018. Errata
Other Texts:
- M. Sonka, V. Hlavac, and R. Boyle, Image Processing, Analysis and Machine Vision, Cengage Learning, 2015.
- S. Birchfield, Image Processing and Analysis, Cengage Learning, 2018.
.
- S. Umbaugh, Digital Image Processing and Analysis, CRC Press, 2011
Prerequisites
CS202 and MATH/STAT 352. If you do not meet the prerequisite requirements for this course, you should see me immediately.
Description/Objectives
Digital image processing is among the fastest growing computer technologies. With increasing computer power, it is now possible to do numerically many tasks that were previously done using analogue techniques. The objective of this course is to provide an introduction to the theory and applications of digital image processing.
Course Outline (tentative)
- Introduction
- Intensity Transformations
- Geometric Transformations
- Spatial Filtering
- Fourier Transform
- Convolution
- Frequency Domain Filtering
- Sampling
- Image Restoration
- Short-Time Fourier Transform
- Multi-resolution Analysis
- Wavelets
- Image Compression
- Applications
Exams and Assignments
Grading will be based on several quizzes, two exams, and 4-5 programming assignments.
Graduate students will be required to present a paper to the rest of the class. Homework
problems will be assigned on a regular basis but will not be collected for grading. Homework
solutions will be made available for each assignment.
Course Policies
Lecture slides, assignments, and other useful information will be posted on
the this web page. Discussion of the of your work is allowed and encouraged. However, each
student should do his/her own work. Assignments which are too similar will
receive a zero. No late work will be accepted unless there is
an extreme emergency. If you are unable to hand in an assignment by the
deadline, you must discuss it with me before the deadline. Both exams will
be closed books, closed notes. If you are unable to attend an exam you must
inform me in advance. No incomplete grades (INC) will be given in this course
and a missed exam may be made up only if it was missed due to an extreme
emergency. Regular attendance is highly recommended. If you miss a class,
you are responsible for all material covered or assigned in class. You should
carefully read the section on Academic Dishonesty found in the UNR Student
Handbook. Your continued enrollment in this course implies that you have read it,
and that you subscribe to the principles stated therein.
Useful Information
- Research
- Important Resources
- Major IP and CV Journals
- Major IP and CV Conferences
- IEEE International Conference on Computer Vision (ICCV)
- IEEE International Conference of Image Processing (ICIP)
- IEEE Computer Vision and Pattern Recognition (CVPR)
- International Conference of Pattern Recognition (ICPR)
- Useful Mathematics, Statistics, and Geometry resources
- Formats and Viewers
- Software
- Computer Vision Library (OpenCV): image processing and computer vision algorithms.
- Matlab: a numeric computation and visualization environment. The image processing and signal processing toolboxes are especially useful. See also: Matlab Tutorial (Univ Utah), Matlab Basics (RPI), Matlab Primer (200K postscript; 25 pages).
- CVIPtools: a GUI-based computer vision and image processing tools, ANSI-C source code and librariesfor Windows95/NT and UNIX, extended computer imaging TCL shell. Also contains an extended Tcl shell with all the computer imaging functions. ANSI-C source code and libraries for image analysis, image compression, image enhancement, image restoration, and many imaging utilities.
- More software ....
- Source Code for Reading/Writing Images
- Debugging
Handouts
Lectures
Homework Assignments
- Homework 1 (intensity transformations, histogram equalization, geometric transformations) (3.11, p 194 >> 3.14, p 240)(3.7, p 194 >> 3.9, p. 240) Solutions
- Homework 2 (Fourier Transform) (4.18, p 306 >> 4.32(a), p 357) (4.19, p 306 >> 4.32(f) p 357) Solutions
- Homework 3 (Frequency Filtering, 1D Convolution) (4.21, p 306 >> 4.45, p 358) (4.33, p 308 >> 4.47, p 359) (4.23, p 307 >> 4.40, p 358) Solutions
- Homework 4 (ignore problem 4) (FFT, 2D Convolution ) (10.12, p 788 >> 10.16, p 868) (10.18, p 790 >> 10.22, p 869) (10.17, p 789 >> 10.21, p 869) Solutions and page 1
- Homework 5 (Image Restoration) (5.11, p 390 >> 5.11, p 442) (5.17, p 391 >> 5.27, p 443) (5.26, p 392 >> 5.42, p 445) Solutions
- Homework 6 (Image Compression) (same problem numbers, p 688) Solutions
Programming Assignments
Presentation Topics
Fingerprint enhancement using STFT analysis Pattern Recognition, 2007.
Histograms of Oriented Gradients for Human Detection IEEE Computer Vision and Pattern Recognition, 2005.
Exposing Digital Forgery from JPEG Ghosts, IEEE Transactions on Information Forensics and Security, vol. 4, no. 1, 2009.
Image Forgery Detection, IEEE SIGNAL PROCESSING MAGAZINE, vol. 16, MARCH 2009.
Watermarking, IEEE Potentials, October/November 2003
Digital image steganography: Survey and analysis of current methods, Signal Processing, 2010
Digital Restoration of Deteriorated Mural Images, 2014 Fifth International Conference on Signals and Image Processing
Fast multiresolution image querying, SIGGRAPH 95
Image Inpainting, SIGGRAPH 2000
Image Restoration using Online Photo Collections, ICCV 2009
Deep Convolutional Neural Network for Image Deconvolution, NIPS 2014
Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections, NIPS 2016
Image morphing: A Survey, Visual Computer 1998.
Schedule of Presentations
Raghav Kaul (Monday, Nov 18th at 1pm): Digital image steganography: Survey and analysis of current methods, Signal Processing, 2010
Lee Easson (Monday, Nov 25th at 1pm): Image Forgery Detection, IEEE SIGNAL PROCESSING MAGAZINE, vol. 16, MARCH 2009.
Bryson Lingenfelter (Monday, Nov 25th at 1:20pm): Deep Convolutional Neural Network for Image Deconvolution, NIPS 2014
Sharif Kamran (Monday, Nov 25th at 1:40pm): Fast multiresolution image querying, SIGGRAPH 95
Paolo De Petris (Wednesday, Nov 27th at 1pm): Watermarking, IEEE Potentials, October/November 2003
Nikhil Vijay Khedekar (Wednesday, Nov 27th at 1:20pm): Digital Restoration of Deteriorated Mural Images, 2014 Fifth International Conference on Signals and Image Processing
Umme Hafsa Billah (Monday, December 2nd at 1pm): Histograms of Oriented Gradients for Human Detection IEEE Computer Vision and Pattern Recognition, 2005.
Nathan Thom (Wednesday, December 4th at 1pm): Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections, NIPS 2016
Thanh Son Nguyen (Wednesday, December 4th at 1:20pm): Image morphing: A Survey, Visual Computer 1998.
Rushikesh Battulwar (Wednesday, December 4th at 1:40pm): Image Inpainting, SIGGRAPH 2000
Song Jiang (Wednesday, December 4th at 2:00pm): Image Restoration using Online Photo Collections, ICCV 2009
Nasif Zaman (Monday, December 9th at 1:00pm): Exposing Digital Forgery from JPEG Ghosts, IEEE Transactions on Information Forensics and Security, vol. 4, no. 1, 2009.
Presentation Guidelines
1. Presentations should be professional as if it was presented in a formal conference (i.e., powerpoint slides/projector).
2. Your goal is to educate and inform your audience. Make sure your presentation follows a logical sequence. Help the audience understand how successive definitions and results are related to each other and to the big picture.
3. You should have your remarks prepared and somewhat memorized. Reading from your notes excessively should be avoided.
4. Anticipate Questions: think of some likely questions and plan out your answer. Understand the Question: paraphrase it if necessary; repeat it if needed. Do Not Digress. Be Honest: if you can't answer the question, say so.
5. Meet the eyes of your audience from time to time.
6. Vary the tone of your voice and be careful to speak clearly and not talk too quickly.
7. Each student's material is different but 15 minutes each should be enough time for your presentation.
Department of Computer Science and Engineering, University of Nevada, Ren
o, NV 89557
Page created and maintained by:
Dr. George Bebis
(bebis@cse.unr.edu)