School of Engineering and Technology, (SET)
 
AT74.06 : Pattern Recognition and Image Processing  3(2-3)
 
Course objectives:

The field of image processing has grown considerably with increased applications in diverse areas as manufacturing, biology, space and medical. Continuous improvements in speed of digital computers, algorithmic development and requirement of a high tech environment makes this field a very active area for academic and industrial research.
 
Learning Outcomes:

Introduction. Image Acquisition and Preprocessing. Image Analysis Techniques. Image Transforms. Object Recognition and Image Understanding. Advanced Research Areas in Machine Vision.
 
Pre-requisite(s):

None
 
Course Outline:
I.             Introduction
1.     Human Vision vs. Machine Vision
2.     Scene Constraints
3.     Camera lens and Optics Theory

II.          Image Acquisition and Preprocessing
1.     Sensors for Image Acquisition
2.     Camera Interfaces and Video Standards
3.     Image Sampling and Quantization
4.     Image Preprocessing: Point, Global and Neighborhood Operations
5.     Image Filters
6.     Edge Detection Techniques

III.       Image Analysis Techniques
1.     Image Segmentation
2.     Edge Based and Region Based Segmentation
3.     Edge Linking and Boundary Detection
4.     Image Matching
5.     Image Feature Extraction
6.     Mathematical Morphology
IV.      Image Transforms
1.     Continuous Image Mathematical Characterization
2.     Discrete Image Mathematical Characterization
3.     Discrete Fourier Transform
4.     Other Image Transforms

V.          Object Recognition and Image Understanding
1.     Knowledge representation
2.     Pattern Classification
3.     Neural Nets

VI.       Advanced Research Areas in Machine Vision
1.     Geometry for 3 D Vision
2.     3 D Objects Representation and Modeling Techniques
3.     Machine Vision: Industrial Application
4.     Robot Vision
 
Laboratory Sessions:
•         Image acquisition
•         Histogram study
•         Convolution and image filter study
•         Edge detection
•         Morphology operation
•         Object recognition
 
Learning Resources:

Textbook:
R. C. Gonzalez, and R. E. Woods: Digital Image Processing, Prentice Hall, 3rd ed., 2007.
 
Reference Books:
1.     R. C. Gonzalez, R. E. Woods, and S. L. Eddins, Digital Image Processing Using MATLAB, Gatesmark Publishing 2nd ed., 2009
2.     Marques, O., Practical Image and Video Processing using MATLAB, Wiley, 2011
3.     Nixon, M., and Aguado A. S. , Feature Extraction and Image Processing for Computer Vision, Elsevier, 3rd ed., 2012
4.     G. A. Awcock and R. Thomas: Applied Image Processing, McGraw-Hill, 1996.
5.     L.J. Galbiati: Machine Vision and Digital Image Processing Fundamentals, Prentice Hall, NJ, 1990.
6.     M. Sonka, V.Hlavac, R. Boyle: Image Processing, Analysis, and Machine Vision, PWS Publishing, NJ, 1999.
 
Journals and Magazines:

International Journal of Computer Vision
Machine Vision and Application - An International Journal
Pattern Recognition
Sensor Review
 
Time Distribution and Study Load:
Lectures: 30 hours
Laboratory sessions: 45 hours
Presentations: 3 hours
Self-study: 90 hours
 
Teaching and Learning Methods:
Lecture with hands-on lab. There will be project at the end of semester when students solve some real-world image processing problem.
 
Evaluation Scheme:
The Final Grade will be computed according to the following weight distribution: Final Exam 35%; Lab./Assignments 20%, Presentation 5%, Project 40%. Open-book examination is given in the final.

An “A” would be awarded if a student can demonstrate clear understanding of the knowledge learned in class as well as from the laboratory assignments and literature reviews.

A “B” would be awarded if a student can understand the basic principles of the knowledge learned in class, from the laboratory assignments and from literature reviews.

A “C” would be given if a student can understand partially the basic principles of the knowledge learned in class, from the laboratory assignments and from literature reviews.

A “D” would be given if a student shows lack of understanding of the knowledge learned in class, from the laboratory assignments and from literature reviews.
 
Instructor(s):
SECTION NAME