CSE 381

Image Processing
Prof. Mahmoud Khalil
Fall 2025
Course Team
• Instructor : Prof. Mahmoud Khalil
• Email: [Link]@[Link]

• Lab TA:

• Communications will be through Teams

2
Grading Scheme
• Students will be evaluated based on the following:
Component % UEL
Student Activities (Project) 35 UEL
One Quiz 5
Midterm exam 20
Final exam 40 UEL

3
Text Books
• Rafael C. Gonzalez and Richard E. Woods, Digital Image
Processing, 4th Edition, Pearson Education, Inc. 2018.,
ISBN: 978‐9353062989

• Richard Sceliski, Computer Vision Algorithms and

Applications, Springer, 2022 (available online for free at:
[Link] ISBN: 978‐1848829343

• OpenCV: [Link]

4
Course Contents
• 2D signals and systems analysis, 2D signals and image
transforms.
• Image formation.
• Image enhancement.
• Image restoration.
• Image coding. Image compression.
• Color image processing.
• Image segmentation.
• Morphological operations.
• Image pyramids.
5
Visual data on the Internet
• Flickr
• 10+ billion photographs
• 60 million images uploaded a month
• Facebook
• 250 billion+ 90% of net traffic
• 300 million a day will be visual!
• Instagram
• 55 million a day
• YouTube
• 100 hours uploaded every minute
6
Visual Sciences

7
Image Processing ‐ Computer Vision

8
What do computers see?

9
Stages of computer vision

• Low‐level
image  image

• Mid‐level
image  features / attributes

• High‐level
features  “making sense”, recognition

10
Low‐level
sharpening

blurring
Adapted from Linda Shapiro, U of Washington

11
Low‐level

Canny

original image edge image

Mid‐level

ORT

data
structure
edge image circular arcs and line segments
Adapted from Linda Shapiro, U of Washington
12
Mid‐level
K-means
clustering
(followed by
connected
component
analysis)

original color image regions of homogeneous color

data
structure

Adapted from Linda Shapiro, U of Washington

13
Low‐level to high‐level

low-level
edge image

mid-level

consistent
high-level line clusters

Adapted from Linda Shapiro, U of Washington

14
Image Enhancement

15
Image Denoising

Salt & Pepper 3 X 3 Average Median

Noise

16
Image Enhancement ‐ Frequency Domain
Original Noisy image Fourier Spectrum

17
Edge Detection

18
Image Segmentation
Goal: identify groups of pixels that go together

19
Optical character recognition (OCR)
Technology to convert scanned docs to text
• If you have a scanner, it probably came with OCR software

Digit recognition, AT&T labs License plate readers

[Link] [Link]
20
Face detection

• Many new digital cameras now detect faces

• Canon, Sony, Fuji, …

21
Smile detection

Sony Cyber-shot® T70 Digital Still Camera 22

Biometrics

Adapted from Anil Jain, Michigan State

23
Vision‐based biometrics

“How the Afghan Girl was Identified by Her Iris Patterns”

Read the story
wikipedia

24
Login without a password…

Face recognition systems now

Fingerprint scanners on
beginning to appear more widely
many new laptops, [Link]
other devices

25
Object recognition (in mobile phones)

Point & Find, Google Goggles

26
Building a Panorama

27
M. Brown and D. G. Lowe. Recognising Panoramas. ICCV 2003
Feature descriptors
• Extraordinarily robust matching technique
• Can handle changes in viewpoint
• Up to about 60 degree out of plane rotation
• Can handle significant changes in illumination
• Sometimes even day vs. night (below)
• Fast and efficient—can run in real time

28
Steve Seitz
Interactive Games: Kinect
• Object Recognition:
[Link]
• Mario: [Link]
• 3D: [Link]
• Robot: [Link]

29
Medical imaging

Image guided surgery

3D imaging
Grimson et al., MIT
MRI, CT

30
Face Landmark Alignment – 3D Persona

What Makes Tom Hanks Look Like Tom Hanks ICCV 2015 31
Smart cars

• [Link]
• Vision systems currently in high‐end BMW, GM, Volvo models

32
Slide content courtesy of Amnon Shashua
Google cars

[Link]
33
AutoCars ‐ Uber bought CMU’s lab

34
2020’s: autonomous vehicles

35
Car Detection and Depth Estimation

36
Vision as a Source of Semantic Information

37
Sports video analysis

Tennis review system

[Link]
38
Computer vision in sports

Virtual pitch markings Free viewpoint video

Sportvision first down line [Canon 2017]

Nice explanation on [Link]
39
Computer vision in sports

Replay Technologies:improving viewer experiences 40

Computer vision in sports

Play tracking 41
Object recognition (in supermarkets)

42
How does it work? Think‐Pair‐Share

43
How does it work?

44
 45
Thanks to Vivek Ramanujan
Human shape capture

46
Human shape capture

47
Human shape capture

48
Human shape capture

49
Why is vision so hard?

posed problem

[Sinha and Adelson 1993]

Adapted from Ali Farhadi, U of Washington

50
Challenges 1: view point variation

Michelangelo 1475-1564

Adapted from L. Fei-Fei, R. Fergus, A. Torralba

51
Challenges 2: illumination

Adapted from Fei-Fei Li

52
Challenges 3: occlusion

Magritte, 1957

Adapted from L. Fei-Fei,

R. Fergus, A. Torralba
53
Challenges 4: scale

Adapted from L. Fei-Fei,

R. Fergus, A. Torralba
54
Challenges 5: deformation

Xu, Beihong 1943

Adapted from L. Fei-Fei, R. Fergus, A. Torralba
55
Challenges 6: background clutter

Adapted from Fei-Fei Li

56
Challenges 7: intra-class variation

Adapted from L. Fei-Fei, R. Fergus, A.

57 Torralba
Visual recognition
Verification

Is this a car?

58
Visual recognition

Classification
:
Is there a car in this picture?

59
Visual recognition
Detection
:
Where is the car in this picture?

60
Visual recognition
Pose Estimation:

61
Visual recognition
Activity Recognition:

What is he What is he doing?

doing?

62
Visual recognition
Object Categorization:

Sky

Person
Tree

Horse
Car

Person
Bicycle
Road
63
Visual recognition
Segmentation

Sky

Tree

Car

Person

64