1 Vision Lec 1

Lecture 1
Introduction to Computer Vision

By : Shimaa Saber
1
Course Ethics
Course Ethics
 Respect Lecture & Sections times.
 Turn off your Mobile.
 DO your course assignments YOURSELF..
 DO your code YOURSELF.
 Read the last lecture before the next one.
 Study before exam.
 Ask to understand.
Agenda
Introduction to Computer Vision
The goal of computer vision
Computer vision Examples
Block Diagram of Computer Vision
Challenges in Computer Vision
4
Introduction to Computer Vision !!
Lecture 1
Course Description
How can computers understand the

visual world of humans?
How can computers See our world?

Human Vision Vs. Computer Vision
7
Human Vision
Human Vision is the process of discovering what is present in

the world and where it is by looking.
Computer Vision
Computer Vision allows the computer to see and understand the

scene
Human
What a person sees

Computer
What a computer sees

Human vs. Computer vision
What can you see in this image? Human Tracking in crowded scene, what you think?
Human is more efficient than computer Computer is more efficient than human
Computer Vision
• Automatic understanding of images
and video.
• Algorithms and representations

allow a machine to recognize
objects, people, scenes, and
activities.
How vision is used now
Examples of state-of-the-art
Some of the following slides by Steve Seitz

 Recognize objects and people
sky
building
flag
face street lamp

banner wall
cars bus
bus
 Forensics
Source: Nayar and Nishino, “Eyes for Relighting”

 Improve photos (“Computational Photography”)
Super-resolution (source: 2d3)

Low-light photography
(credit: Hasinoff et al., SIGGRAPH ASIA 2016)
Depth of field on cell phone camera (source: Inpainting / image completion

Google Research Blog) (image credit: Hays and Efros)
Why study computer vision?
 Billions of images/videos captured per day
• Huge number of useful applications

• The next slides show the current state-of-the-art
Computer vision Examples
Examples of state-of-the-art
Some of the following slides by Steve Seitz

Optical character recognition (OCR)
Digit recognition, AT&T labs (1990’s) License plate readers
Automatic check processing

Face detection
 Nearly all cameras detect faces in real time

Face Recognition
Vision-based biometrics
“How the Afghan Girl was Identified by Her Iris Patterns” Read the story
Source: S. Seitz
Login without a password
Fingerprint scanners on many Face unlock on Apple iPhone X

new smartphones and other See also http://www.sensiblevision.com/
devices
Bird Identification
Merlin Bird ID (based on Cornell Tech technology!)

Sports
Sportvision first down line

Nice explanation on www.howstuffworks.com
Source: S. Seitz
Face makeovers
Medical imaging
3D imaging (MRI, CT)
Skin cancer classification with deep learning

https://cs.stanford.edu/people/esteva/nature/
Virtual & Augmented Reality
Hand & body tracking

6DoF head tracking
3D scene understanding 3D-360 video capture

Smile detection
Sony Cyber-shot® T70 Digital Still Camera

3D from thousands of images
Building Rome in a Day: Agarwal et al. 2009

Special effects: shape capture
The Matrix movies, ESC Entertainment, XYZRGB, NRC

Special effects: motion capture
Pirates of the Carribean, Industrial Light and Magic

Smart cars
Vision in space
NASA'S Mars Exploration Rover Spirit captured this westward view from atop
a low plateau where Spirit spent the closing months of 2007.
Vision systems (JPL) used for several tasks

• Panorama stitching
• 3D terrain modeling
• Obstacle detection, position tracking
• For more, read “Computer Vision on Mars” by Matthies et al.
Industrial robots
Vision-guided robots position nut runners on wheels

What is Computer Vision?
37
Computer Vision Meaning
 Computer vision is an interdisciplinary scientific field that
deals with how computers can gain high-level understanding
from digital images or videos.
 Computer vision is a field of artificial intelligence (AI) that

enables computers and systems to derive meaningful
information from digital images, videos, and other visual
inputs and take actions or make recommendations based on
that information.
Block Diagram of Computer Vision
Pre- Feature Decision

input Segmentation
processing extraction making
•Noise reduction •Detecting

•Selecting
•Image enhancement important
image interested
•Color correlation point
area
•Scaling
39
What is Computer Vision?
Relation with other sciences
Why is computer vision difficult?
43
Viewpoint variation
Scale
Illumination
Motion (Source: S. Lazebnik)
Intra-class variation
Background clutter
Course Materials
1. Lecture Powerpoint Slides
2. Lecture Notes
3. References
4. Solved Problems
References
 Image Processing, Analysis, and Machine

Vision
by Milan Sonka, Vaclav Hlavac, and Roger Boyle
 Computer Vision: Algorithms and

Applications
by Richard Szeliski.
Course Prerequisites
 Good knowledge about Digital Signal Processing
 Good programming skills (Recommended computer
languages: Matlab, python
 Self-learning skills
 Good research skills
 Work in teams with self- dependence for ending your
tasks
49

1 Vision Lec 1

Uploaded by

Copyright:

Available Formats

1 Vision Lec 1

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

1 Vision Lec 1

Uploaded by

Copyright:

Available Formats

Lecture 1

Introduction to Computer Vision

The goal of computer vision

Computer vision Examples

Block Diagram of Computer Vision

Challenges in Computer Vision

How can computers understand the

How can computers See our world?

Human Vision is the process of discovering what is present in

Computer Vision allows the computer to see and understand the

What a person sees

What a computer sees

• Algorithms and representations

Some of the following slides by Steve Seitz

face street lamp

Source: Nayar and Nishino, “Eyes for Relighting”

Super-resolution (source: 2d3)

Depth of field on cell phone camera (source: Inpainting / image completion

• Huge number of useful applications

Some of the following slides by Steve Seitz

Digit recognition, AT&T labs (1990’s) License plate readers

Automatic check processing

 Nearly all cameras detect faces in real time

Fingerprint scanners on many Face unlock on Apple iPhone X

Merlin Bird ID (based on Cornell Tech technology!)

Sportvision first down line

3D imaging (MRI, CT)

Skin cancer classification with deep learning

Hand & body tracking

3D scene understanding 3D-360 video capture

Sony Cyber-shot® T70 Digital Still Camera

Building Rome in a Day: Agarwal et al. 2009

The Matrix movies, ESC Entertainment, XYZRGB, NRC

Pirates of the Carribean, Industrial Light and Magic

Vision systems (JPL) used for several tasks

Vision-guided robots position nut runners on wheels

 Computer vision is a field of artificial intelligence (AI) that

Pre- Feature Decision

•Noise reduction •Detecting

Motion (Source: S. Lazebnik)

 Image Processing, Analysis, and Machine

 Computer Vision: Algorithms and

You might also like