Department of Computer Science and Engineering

• Email: bebis@cse.unr.edu
• Phone: (775) 784-6463
• Office: 411 WPEB
• Office Hours: MW 2:30pm - 4:00pm

• Email: anovonty@nevada.unr.edu
• Office: 414 WPEB (Computer Vision Lab)
• Office Hours: TR 10:30am - 1:00pm

• 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

Digital image processing is among the fastest growing computer technologies. This course will provide an introduction to the theory and applications of digital image processing. In particular, this course will introduce students to the fundamental techniques and algorithms used for processing and extracting useful information from digital images.

Course Outline (tentative)

• Introduction
• Intensity & Geometric Transformations
• Spatial Filtering & Convolution
• Fourier Transform & Frequency Domain Filtering
• Sampling and Aliasing
• Image Restoration
• Image Compression
• Short-Time Fourier Transform
• Multi-resolution Representations & Wavelets (if time permits)

Exams and Assignments

Course Policies

Useful Information

• Major IP and CV Journals
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)
  • Computer Vision and Image Understanding (CVIU)
  • International Journal of Computer Vision (IJCV)
  • Image and Vision Computing (IVC)
  • IEEE Transactions on Image Processing (TIP)
  • Pattern Recognition (PR)
  • Machine Vision and Applications (MVA)
  
  
  
• 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)
    
  
  
  
• Formats and Viewers
  • Image Formats and Viewers
    
  • Image formats
    
  • Xv is an interactive image display program for the X window system that is useful for displaying and editing images in a variety of formats.
  • Irfanview (freeware graphic viewer for Windows)
  • GISLook (PGM support on Mac)
  
  
  
• Source Code for Reading/Writing Images
  • C routines to read/write .pgm images ReadImage.c WriteImage.c and an example Threshold.c
    
  • C++ routines to read/write .pgm images ReadImage.cpp WriteImage.cpp and an example Threshold.cpp
    
  • C++ routine to read the header of a PGM or PPM image: ReadImageHeader.cpp
    
  • The image class: image.h and a simple implementation image.cpp
    
  • A makefile for the Threshold example
    
  
  
  
• Other
  • Math Cheat Sheet (lots of useful formulas)
  • Numerical Recipes in C
  • ddd: GNU debugger

Handouts

• Syllabus
  


• Math Review Material (from textbook)
  

Sample Exams

• Midterm Exam and Solutions


• Midterm Review
  


• Final Exam and Solutions


• Final Review
  

Lectures

• Overview
  


• PGM Image File Format
  


• Introduction to Image Processing
  


• Intensity Transformations
  
  
• Arithmetic, Logical, and Geometric Transformations
  
  
• Spatial Filtering
  
  
• Math Review
  


• Fourier Transform (see also Fourier Transform Pairs 1 and Fourier Transform Pairs 2)


• Fast Fourier Transform (FFT)
  


• Convolution
  


• Sampling and Aliasing
  


• Frequency Filtering
  
  
• Image Restoration
  


• Image Compression (also, see Image Compression Techniques and Survey)
  

Programming Assignments

• Image Database
  
  
• Team Members (revised on 9/8/2021 at 2:30pm)
  
  
• Submission Instructions
  
  
• Pogramming Assignment 1 (Due date: 9/22/2021)
  
  
• Pogramming Assignment 2 (Due date: 10/13/2021)
  Pattern.pgm and Image.pgm
  
  
• Pogramming Assignment 3 (Due date: 11/3/2021) fft.c, documentation, Rect_128.dat
  


• Programming Assignment 4 (Due date: 11/29/2021) (download boy_noisy.gif and girl.gif)
  Adding Gaussian noise using Box Muller method: link1 and link2
  
  

Presentation Topics (Graduate Students Only)

Watermarking, IEEE Potentials, October/November 2003 (Steve Carlson, December 1, 1:00pm - 1:20pm) Slides

Online Signature Verification Using Fourier Descriptors (Andrew Washburn, December 1, 2021, 1:20pm - 1:40pm) Slides

Image Forgery Detection, IEEE SIGNAL PROCESSING MAGAZINE, vol. 16, MARCH 2009 (Tolga Karakurt, December 1, 2021, 1:40pm - 2:00pm) Slides

On the use of phase of the Fourier transform for face recognition under variations in illumination(Di Xiao, December 1, 2021, 2:00pm - 2:15pm) Slides

Histograms of Oriented Gradients for Human Detection IEEE Computer Vision and Pattern Recognition, 2005 (Ryan Gorman, Dec 3, 2021, 1pm-1:20pm) Slides

Digital Restoration of Deteriorated Mural Images, 2014 Fifth International Conference on Signals and Image Processing (Allan Romero, Dec 3, 2021, 1:25pm - 1:45pm) Slides

Image Restoration using Online Photo Collections, ICCV 2009 (Mark Mccord, Dec 3, 2021, 1:50pm - 2:10pm) Slides



Fingerprint enhancement using STFT analysis

Digital image steganography: Survey and analysis of current methods, Signal Processing, 2010

Image Inpainting, SIGGRAPH 2000

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 20 minutes each should be enough time for your presentation.