---

ECE 438 Image Analysis & Computer Vision

Course Syllabus

---

Professor: Dr. Scott E Umbaugh Office: Engineering Building, Room EB3037

Phone: 650-2524, 2948 e-mail: sumbaug@siue.edu

Textbook: Computer Imaging: Digital Image Analysis and Processing , SE Umbaugh, CRC Press, 2005

Prerequisite: ECE 351 and programming experience, or consent of instructor

Class Format: Two lectures and 1 lab/homework per week, two tests, term project

Web Site Imaging Examples: CVIPtools Imaging Examples

Goals and Objectives: To introduce the student to computer vision algorithms, methods and concepts which will enable the student to implement computer vision systems with emphasis on applications and problem solving. Lab exercises will familiarize the student with typical hardware as well as software development tools. Students will use the C programming language to implement computer vision algorithms.

---

OUTLINE

• Introduction and Image Sensing 4 Lectures
• Image Analysis 4 Lectures
• Edge/Line Detection 4 Lectures
• TEST #1
• Segmentation/Morphological Filtering 4 Lectures
• Fourier Transform 2 Lectures
• Feature Extraction/Analysis 4 Lectures
• Pattern Classification 2 Lectures
• TEST #2
• PROJECT DUE -- 16th week

Project will be some application of computer vision to digital image(s). Typical projects are simple pattern classification applications using CVIPtools libraries.

GRADING: Test #1 - 25%, Test #2 - 25%, Lab Exercises & Homework - 25%, Project - 25%

---

ECE 438 LECTURE SCHEDULE

Ø Homework is due the first class period the week after assigned; 4 homework problems will be randomly selected from each set for grading

WEEK	TOPICS	READING	HOMEWORK & LAB
1	Overview, computer imaging systems, lenses	pp. 3-11, 15-26	Chap 1: 1-6 Chap 2: 1-4,6,9,11,12
2	Image formation and sensing, CVIPlab	pp. 26-57, 551-573	Chap 2:13-15,21,25,27,29 Program: 2.7.1
3	Image analysis, preprocessing	pp. 67-93	Chap 3: 1,2,3,6,9,10,12,21 Program: 3.6.2, parts 1,2,5
4	Binary image analysis	pp. 93-109	Chap 3: 23,25,26,28,29 Program: 3.6.5, parts 1-3
5	Edge detection	pp. 121-135	Chap4:1-6,9,11,14,15 Program: 4.6.1
6	Edge detection performance, Hough transform	pp. 135-151	Chap 4: 17-21 Not collected due to test
7	Review and TEST #1 Sample test KEY
8	Segmentation	pp. 151-168	Chap 4: 22-26 Program: 4.6.4
9	Morphological filtering	pp. 168-183	Chap 4: 27-30 Program: 4.6.6, 4.6.5 for extra credit
10	Fourier transform Project proposal due	pp. 201-220	Chap 5: 1-8 Project
11	Feature extraction, shape, histogram, color, spectral, texture, using CVIPtools	pp. 261-278	Chap 6: 1-4, 8,11,13,14, 16,17 Project
12	Feature analysis, feature vectors, distance /similarity measures, data preprocessing	pp. 278-285	Chap 6:18-22 Project
13	Pattern classification	pp. 285-291	Chap 6: 23-26,28 Project
14	Projects		Project
15	Review and TEST #2 Sample test KEY
16	Demonstrate term project to professor and TA Final Project paper due

---

ECE 438 Image Analysis & Computer Vision - Semester Project

Semester Project: The project will consist of designing experiments, implementing algorithms, and analyzing the results for a computer vision problem. You can work alone or with a partner. The project will be selected by the students**, subject to approval by the professor. A paper will be written describing the project and discussing what was learned during the project. The final paper should be about 8 to 15 pages, typed and double-spaced; include images ! In the paper include an appendix containing related data files and/or program listing(s). The students will give a short presentation of their project in the lab to the class, the professor, and the lab instructor.

Grading: The project is worth 25% of your term grade, broken down as follows:

• Overall Project.. 15%
• Paper................. 5%
• Presentation........ 5%

NOTES: 1) Start on your project as early in the term as possible, 2) late projects are worth 0.

If you need specific types of images for your project that you cannot get yourself:, such as X-ray, MRI, etc, look here: Image Databases

============================================================================================

**Fall 2007 Project: This semester the entire class will be doing a project that consists of performing three lab exercises. Therefore, no proposal is necessary. These exercises are related to using images from the new 3-D camera that the department has recently acquired. You are to work in groups of two and work together on all aspects of the project. When you write the report and give the presentation, include a brief discussion of individual contributions to the project. The files for the project are available here, the first three are the required Word documents for the labs, and the last is the image database

Project Files: Project Overview, Lab1, Lab2, Lab3, Image Database

Possible Project Topics:

• 1) Recognition of geometric shapes, e.g. circles, squares, rectangles, triangles, etc.
• 2) Classification of different tools, e.g. screwdrivers, wrenches, hammers, etc.
• 3) Identification of different coins and bills.
• 4) Design a program to read bar codes.
• 5) Character recognition.
• 6) Tableware classification for robot
• Other projects of your choice with emphasis on applications of pattern recognition/classification

Important Note: Your project needs to work with real world input, i.e. the camera or scanner. You need to design it to be robust, i.e. to handle various sizes, orientations, lighting conditions, etc. If it cannot handle these you need to define a calibration routine that is easy and fast. As part of the demo we will test the robustness via having the program classify "unknown" input.

Week What is due

• 10 (or sooner) Brief, 1 page, project proposal
• 16 Final project paper due short demonstration to professor and lab instructor

Suggested Project Process:

• 1) Define the problem
• 2) Design experiment(s) you wish to pursue
• 3) Design algorithms/C function(s) to implement related to project, or use CVIPtools
• 4) Code and debug your function(s)
• 5) Test your functions on some real images
• 6) Process images/do the experiments
• 7) Compare and contrast your results to other similar results from using CVIPtools functions, or research results in library from similar experiments - Analyze results using appropriate metrics, tabulate or plot, etc.
• 8) Write report, include images
• 9) Demonstration to the class
• For more details on using CVIPtools with your project, go here

· NOTE: If you do not have any specific images that you want to use, take a look at the image databases on the Internet, such as: DIP Image Databases

---

ECE 438 Image Analysis and Computer Vision Laboratory Outline

Ø Homework and program listings will be handed in at the beginning of the first class period the week after assigned

Ø Late homework and lab work is worth 50% up until 2 days late, after that it is worth 10%

Ø Useful document for those familiar with C++, but not C programming: C for C++ Programmers.htm

Week	TOPICS - reading: Section 2.3, Chapter 11, CVIPtools
1&2	2.7.1 Introduction to CVIPlab
3	3.6.2 parts 1,2 and 5, Arithmetic/Logic Operations,
4	3.6.5, parts 1-3 Connectivity and Labeling
5	4.6.1 Edge Detection – Roberts and Sobel
6	(Study)
7	(Test #1)
8	4.6.4 Histogram Thresholding Segmentation
9	4.6.6 Iterative Morphological Filters; EXTRA CREDIT: 4.6.5 Morphological Filters
10	Project proposal due.
11-15	Work on project: application of pattern classification
16	Present project to the class

---

ECE 438 Image Analysis & Computer Vision PowerPoint Lecture Slides

CVIPbook_PPLec\Chapter1.ppt

CVIPbook_PPLec\Chapter2.ppt

CVIPbook_PPLec\Chapter3.ppt

CVIPbook_PPLec\Chapter4.ppt

CVIPbook_PPLec\Chapter5FFT.ppt

CVIPbook_PPLec\Chapter6.ppt

Brief Bibliography

Books

• Computer Imaging: Digital Image Analyis and Processing , Scott E Umbaugh, The CRC Press, Boca Raton, FL, January 2005

· 1a. Computer Vision and Image Processing: A Practical Approach Using CVIPtools - S. E Umbaugh, Prentice Hall PTR, Upper Saddle, NJ, 1998

• 1. Digital Image Processing - R.C.Gonzalez & P.Wintz
• 2. Robot Vision - B.K.P.Horn
• 3. Computer Vision - D.H.Ballard & C.M.Brown
• 4. Syntactic Pattern Recognition : An introduction -R.C.Gonzalez and M.G.Thomason
• 5. Pattern Recognition - A Statistical Approach - P.A. Devijver and J. Kittler
• 6. Digital Image Processing - W. K. Pratt
• 7. Fundamentals of Digital Image Processing - A.K. Jain
• 8. Digital Picture Processing - A. Rosenfeld and A.C. Kak
• 9. Pattern Classification and Scene Analysis - R.O. Duda and P.E. Hart
• 10. Object Recognition by Computer - W.E.L. Grimson
• 11. Digital Pictures - A.N. Netravali and B.G. Haskell
• 12. Vision in Man and Machine - M.D. Levine
• 13. Pattern Recognition Statistical, Structural and Neural Approaches, R.J Schalkoff, John Wiley & Sons NY
• 14. Digital Image Processing and Computer Vision, R.J. Schalkoff, Wiley
• 15. Artificial Intelligence: An Engineering Approach, R.J. Schalkoff, McGraw-Hill
• 16. Algorithms for Graphics and Image Processing, Theo Pavlidis, Computer Science Press, call no.: T385.P381982
• 17. Handbook of Pattern Recognition and Image Processing, K.S. Fu and T.Y. Young, Academic Press
• 18. The Image Processing Handbook, John C. Russ, CRC Press SIUE Library call #: TA1632.R881992 (reference)

Journals

• 1. IEEE Transactions on Pattern Analysis and Machine Intelligence
• 2. IEEE Transactions on Computers
• 3. Pattern Recognition
• 4. Computer Vision, Graphics and Image Processing
• 5. IEEE Transactions on Medical Imaging
• 6. Computerized Medical Imaging and Graphics
• 7. IEEE Transactions on Image Processing
• 8. IEEE Engineering in Medicine and Biology
• 9. IEEE Transactions on Signal Processing
• 10. IEEE Transactions on Neural Networks
• 11. IEEE Transactions on Geoscience and Remote Sensing
• 12. Photogrammetric Engineering and Remote Sensing
• 13. International Journal of Remote Sensing
• 14. Journal of Visual Communication and Image Representation

Numerous Conference Proceedings from the following professional groups:

• IEEE - Institute of Electrical and Electronic Engineers
• SPIE - Society of Photographic and Instrumentation Engineers, The International Society for Optical Engineering
• SMPTE - The Society of Motion Picture and Television Engineers
• PRS - Pattern Recognition Society