BMI Course Information
BMI 591 Introduction to Digital Image Processing (3)
Instructor Information |
|
Fall 2009 |
|
Spring 2009 |
Course not offered |
Catalog Description
This course is a core course in imaging informatics with the focus on the principles of digital image processing and analysis. The first part of the course introduces the basics of image processing (e.g., point and neighborhood processing, image geometry, Fourier transform, image restoration, image segmentation, mathematical morphology, image topology, shapes and boundaries, color processing, image coding and compression, wavelet, and special effects), and the second part of the course covers advanced topics in image analysis (e.g., K-means and fuzzy C-means clustering, nonlinear diffusion filtering, PDE-based image filtering, mixture modeling, Markov random field-based image segmentation, parametric and geometric deformable models). As an introduction course, it involves minimal mathematics, and is software (matlab) oriented and has a plenty of examples and excises, and highlights applications with images from medicine and biology. This course is specially designed at the request of our BMI students who attended my class in the last semester.
Prerequisites
BMI graduate student, or by permission of instructor
Textbook and Other Materials
Textbooks
1. Alasdair McAndrew. Introduction to Digital Image Processing, Course Technology; 1 edition (2005)
2. Omer Demirkaya, Musa H. Asyali, Prasanna K. Sahoo. Image Processing with MATLAB: Applications in Medicine and Biology. CRC; 1 edition (2009)
Reference books
1. Bernd Jδhne, Digital Image Processing. Springer-Verlag; 6th edition, 2005
2. Isaac Bankman. Handbook of Medical Imaging: Processing and Analysis. Academic Press; 2st edition, 2009
3. Lawrence O'Gorman Michael J. Sammon, Michael Seul. Practical Algorithms for Image Analysis. Cambridge University Press; 2 edition 2008
Course Learning Outcomes
At the completion of the course, student will be well versed with basic knowledge in digital image processing and possess the necessary skills to apply the learnt skills on problems in biomedical domain.
Understand general terminology of digital image processing
Master various image types, intensity transformations and spatial filtering
Familiarize Fourier transform for image processing in frequency domain
Understand the methodologies for image segmentation, restoration, topology, etc.
Demonstrate skills in implementing image processing algorithms.
Major Topics and Time Covered
point and neighborhood processing,
image geometry,
Fourier transform,
image restoration,
image segmentation,
mathematical morphology,
image topology,
shapes and boundaries,
color processing,
image coding and compression,
wavelet
special effects
K-means and fuzzy C-means clustering,
nonlinear diffusion filtering,
PDE-based image filtering,
mixture modeling
Markov random field-based image segmentation
parametric and geometric deformable models