Beng445a/Eeng445a/Enas912a

Biomedical Image Processing and Analysis

Fall 2014

originalblurredlow samplingedges


Resources page: For information on course resources for computer (Matlab) assignments.
Engineering Information Technology: For information on computing resources in Engineering (circus, garage).
Yale Classes server (use v2): For course information, under "Resources": slides, handouts, problem sets, etc.


Course Number

BENG/EENG 445, ENAS 912

Course Title

Biomedical Image Processing and Analysis

Instructors

James Duncan (james dot duncan at yale dot edu)
Lawrence Staib (lawrence dot staib at yale dot edu)

Teaching Assistant

TBN (at yale dot edu)
TA office hours: TBA
Office: TBA
Other times by appointment.

Schedule

MW 4:00-5:15 at TBN

 

Overview

This course is an introduction to Biomedical Image Processing and Analysis covering image processing basics and techniques for image enhancement, compression, segmentation, registration and motion analysis. Students will learn the fundamentals behind image processing and analysis methods and algorithms with an emphasis on biomedical applications. This course is open to undergraduate and graduate students. We assume students have an understanding of linear systems (Eeng 310 or equivalent) and calculus up to differential equations. In addition, it is also helpful to have a familiarity with elementary probability theory. Please contact the instructors if you have questions regarding your preparation. There will be about ten homeworks and both a midterm and a final exam (during exam period). Homeworks will include Matlab programming assignments. Grading will be based approximately 1/3 on the homeworks, 1/3 on the midterm and 1/3 on the final. Undergraduates and graduates are graded separately; in addition, assignments may differ.

Text:

R. Gonzalez and R. Woods, Digital Image Processing, Prentice Hall (Book Website)

(On reserve in the Engineering Library.)

Chapters 1 and 2 online

Additional readings to be distributed during class.

Course Objectives:

Having successfully taken this course, you will be able to

 

Course Outline (dates/topics approximate), Fall 2014

Introduction (Read Gonzalez Ch. 1)

Aug 27

ls

Intro/Organization

Fundamentals (Read Gonzalez Ch. 2)

Aug 29

ls

Basics / Digitization

Sep 1

 

Labor Day – no class

Sep 3

ls

Gray scale enhancement

Enhancement (Read Gonzalez Ch. 3)

Sep 8

ls

Spatial Filtering

Sep 10

ls

Spatial Filtering

Sep 15

ls

Mathematical Morphology (Gonzalez Ch. 9.1-9.3) (to be rescheduled)

 

 

Enhancement (Read Gonzalez Ch. 4)

Sep 17

jd

Enhancement in the frequency domain

Sep 22

jd

Enhancement in the frequency domain

Sep 24

jd

Enhancement in the frequency domain

Compression (Read Gonzalez Ch. 8)

Sep 29

jd

Compression

Oct 1

jd

Compression

 

 

Rigid and Nonrigid Registration (Read handout)

Oct 6

ls

Registration: Introduction and Transformations

Oct 8

ls

Registration: Match Metrics

Oct 13

ls

Registration: Match Metrics

Oct 15

Midterm Review

Oct 20

 

Midterm Exam

Oct 22

 

October Recess – no class

Oct 27

ls

Registration: Optimization and Interpolation

Oct 29

ls

Registration: Robust

Motion (Read handout)

Nov 3

jd

Motion

Nov 5

jd

Motion

Segmentation (Read Gonzalez Ch. 10 and handout)

Nov 10

jd

Motion

Nov 12

jd

Segmentation

Nov 17

jd

Segmentation

Nov 19

jd

Segmentation

Nov 24

Thanksgiving Break – no class

Nov 26

Thanksgiving Break – no class

Dec 1

jd

Segmentation

Dec 3

ls

Diffusion Weighted Image Analysis

Dec 8

Reading Period – schedule Review

Dec 16

Final Exam, 9:00 a.m.


Image Processing Links:

Gonzalez and Woods: Digital Image Processing

Image Database

Image Processing Tutorials

 

Image Processing Fundamentals by Young Gerbrands and van Vliet

Tutorials on Image Analysis, Computer Vision

Image Processing (wikipedia)

Image Processing Tutorial

A-Z of Image Processing Concepts

efg 's Image Processing Page

One dimensional convolution demonstration: you can draw your own functions or select pre-defined ones.

Two dimensional filtering demonstration: first, Fourier transform, then view the magnitude log; apply Gaussian smoothing or other filtering, then inverse transform.

Discrete Fourier Theory (1D)

Matlab Tutorials

Mathworks

Introduction to Image Compression

Deformable Image Segmentation

Homogeneous Coordinates

Image Registration Bibliography

HIPR2: Image Processing Learning Resources with JAVA

Pilot European Image Proc. Archive

The Graphics File Format Page

Watermarking, steganography, information hiding

StirMark:Watermarking Robustness Test

Morphing

 

Amara's Wavelet Page

Principles of Computerized Tomographic Imaging

Computer Vision Home Page

Computer Vision On-line Bibliography

 

Aug 2014