Scribd
Upload
56 views20 pages

L1 Introduction

Uploaded by

Gary Fung
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
56 views20 pages

L1 Introduction

Uploaded by

Gary Fung
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 20

Image Processing and Analysis

MSBD 5010
Fall 2024

Instructor: Albert Chung


Department of Computer Science and Engineering (CSE)
The Hong Kong University of Science and Technology

Email: [email protected]

Instructor office: Room 3510, CSE

Instructor webpage: http://www.cse.ust.hk/~achung


MSBD 5010
• Lecture: Tuesdays, 7:30 pm
• Venue: Room 2465, Lift 25-26
• Class Dates: Sept 2, 2024 – Nov 30, 2024
• Lecture notes will be available online
• Office Hours: by appointment. I am happy to meet you. Feel free to drop me
an email if you have any questions.
• No lab and no tutorial
• Personal Homepage: www.cse.ust.hk/~achung
• Teaching Assistant: Hazel Ziyi He, [email protected]
Computing requirements
• We will use Python and approved packages for the
assignments
• There are workstations available in HKUST ITSC Computer
Barns, https://itsc.hkust.edu.hk/services/academic-
teaching-support/facilities/computer-barn , for you to
work on the assignments
• A good reference for review, https://learnpython.org/
• Please review and learn Python programming for image
processing
Expected background and related courses

• Basic partial derivatives, differential equations, and


multiple integrals
• Data Structures, Algorithms, Programming in Python
• Basic linear algebra, e.g., eigenvalues and eigenvectors
• Basic statistics and probability
Course topics
Topics (Tentative)
1. Introduction, Image Fundamentals
2. Enhancement in the Spatial Domain (Bilateral filter, Canny Edge Detector)
3. Enhancement in the Frequency Domain
4. Restoration and Filtering (Denoising and Super-Resolution)
5. Morphological Image Processing
6. Color Image Processing
7. Segmentation of Images (Hough transform, statistical models, active contour
models, deep learning segmentation methods)
8. Registration of Images (rigid registration, affine registration, similarity
measures, non-rigid registration, deep learning registration methods)
9. Feature Descriptors, e.g., Local Binary Patterns, Scale Invariant Feature
Transform, Oriented FAST and Rotated BRIEF
10. Image Compression
11. Image Classification
12. Object Detection / Defect Detection / AI+Healthcare / Other related topics
(face, iris or object recognition)
Course outcomes
On successful completion of this course, students are expected to be
able to

1. Identify basic image enhancement techniques in both the spatial


and frequency domains
2. Enhance an image in the presence of noise and distortion
3. Apply basic morphological image processing techniques
4. Segment image components from an image
5. Register images with similarity metrics and transformations
6. Compress an image with lossless or lossy compression methods
7. Represent and describe an image using different feature descriptors
8. Learn image analysis applications
Course references

• Reference books:
• Digital Image Processing, Gonzalez and Woods, Forth Edition, Prentice
Hall, 2018
• Computer Vision Algorithms and Applications, Richard Szeliski, Second
Edition, Springer, 2022
• Feature Extraction and Image Processing for Computer Vision, Mark
Nixon & Alberto Aguado, Third Edition, Academic Press, 2012
• Computer Vision A Modern Approach, Forsyth & Ponce, Second Edition,
Person, 2012

• More references will be listed in the lecture notes.


Course requirements and grading scheme
• Homework Assignments (30%):
• Three assignments
• Both written and programming assignments
• Assignments must be submitted by 11:59 pm of the due date
• Late assignments will incur a 10% penalty
• Assignment submissions with more than one day late will not be
accepted
• If you have trouble, please don’t hesitate to email us as soon as
possible

• Final Examination (70%):


• Exam format: in-person, written
• Venue: To be confirmed, 3 hours
What is Image Processing?

• Processing of “pictorial” information


• Processing of information obtained from images

Image Process Output

f(x,y)
Find a face from an image

Problem: How to find a face in an image?


Information based on
Image Intensity
Information based on Image Intensity
and after processing
After processing of information,
we find a face
• The use of algorithms to process digital
images

• Enhanced
Digital images
Algorithms • Features
images
(2D or 3D) • Objects
• Class
labels
Two principal applications
Machine Perception
Derived useful information
[Edges, Corners, Regions, Objects,
Class Label, . . . ]
Used for further “Machine” Processing,
e.g., face detection, object detection,
Image Process
object tracking, diagnosis, etc.

Human Perception
New Image
Often
“perceptually”
enhanced, e.g.,
image
enhancement for
fingerprint
analysis.
Two principal applications
• Machine Perception

• Human Perception

Image has 2 colors Still has two colors


(perceptually clearer)
Two words: image processing
• image
– Fundamentals
• Image formation based on individual elements
(pixels)
– Representations
• Sampling and Quantization
• Colors
• Alternative representations (Transforms), e.g.,
image formation based on frequency coefficients,
or basis images.
Two words: image processing

• processing
– manipulation of the image data
• Enhancement and Restoration
• Geometric transformations, e.g., rotation, scaling.
• Segmentation
• Registration
• Compression
• Classification
Examples of image processing usage
Where does image processing fit in?

Computer
Vision

Computer Image
Graphics Processing

You might also like