SlideShare una empresa de Scribd logo
1 de 25
Descargar para leer sin conexión
30/01/20 1
Kim Steenstrup Pedersen
Associate Professor, Ph.D.
Head of IMAGE Section
Dept. of Computer Science
The pros and cons
of modern AI &
computer vision
What is modern Artificial Intelligence (AI)?
30/01/20 2
Machine Learning
Bioinformatics
Information
Retrieval
Medical Image
Analysis
Audio /
Speech
Analysis
And more …
Computer
Vision
Natural
Language
Processing
I am here
Robotics
Oxford Dict. Def.: The theory and development of computer systems able to
perform tasks normally requiring human intelligence, such as visual perception,
speech recognition, decision-making, and translation between languages.
There is no clear definition (that all agrees upon) of what AI is!
What is machine learning?
30/01/20 3
Data is represented as points x in some high dimensional space.
Learn = Estimate a function (model) that groups / separate items in
this space.
y(x;w) ! Apple,Pear{ } A classification
problem with two
classes
•  We need data in order to learn the function /
parameters.
•  We call this training data and we also talk about
validation and test data.
•  Approaches to machine learning:
•  Supervised learning: We have training data examples of both
the input and wanted output
•  Unsupervised learning: We only have training data examples
of the input
•  And combinations thereof: Semi-supervised, active learning,
reinforcement learning, …
What is machine learning?
30/01/20 4
x1= , y1=Apple x2= , y2=Pear x3= , y3=Pear
x1= , y1=? x2= , y2=? x3= , y3=?
What is machine learning?
30/01/20 5
The goal is to make as few mistakes on the training set as possible
and to make good predictions on new unseen data (test data)
y(x;w) ! Apple,Pear{ }
?
What is Computer Vision?
My definition: The design of algorithms for interpreting visual data by
mimicking (and surpassing) the human visual perceptual system.
Computer Vision
30/01/20 7
Railroad asset mapping: Detection of
signals, signs, cabinets etc.
Articulated tracking of humans
Some research highlights:
Digital natural history: Specimen
detection, species recognition,
automatic label reading
Object recognition and detection
What is in this image?
“Car”
“Window”
“Lamp post”
Where?“a car” or “street scene”
Recognition: Detection:
How do we represent an image in the
computer?
R:101
G: 24
B: 18
R:100
G: 23
B: 17
R:103
G: 24
B: 17
R:102
G: 23
B: 16
R:104
G: 24
B: 17
R:104
G: 24
B: 17
R:108
G: 25
B: 17
R: 98
G: 23
B: 17
R:101
G: 24
B: 18
R:100
G: 23
B: 17
R:103
G: 24
B: 17
R:102
G: 23
B: 16
R:103
G: 23
B: 16
R:104
G: 24
B: 17
R:107
G: 24
B: 16
R: 98
G: 23
B: 17
R:102
G: 25
B: 19
R:101
G: 24
B: 18
R:102
G: 23
B: 16
R:103
G: 24
B: 17
R:103
G: 23
B: 16
R:104
G: 24
B: 17
R:109
G: 24
B: 17
:100
: 23
: 15
:102
: 25
: 17
:101
: 24
: 16
:102
: 23
: 16
:104
: 25
: 18
:103
: 23
: 14
:104
: 24
: 15
:108
: 23
: 16
R:104
G: 24
B: 17
R: 98
G: 25
B: 19
R:100
G: 22
B: 18
R:101
G: 23
B: 19
R:104
G: 23
B: 19
R:103
G: 22
B: 18
R:106
G: 23
B: 17
R:105
G: 22
B: 16
R:107
G: 24
B: 18
R:102
G: 25
B: 19
R:101
G: 24
B: 18
R:101
G: 24
B: 18
R:104
G: 25
B: 18
R:101
G: 22
B: 15
R:105
G: 25
B: 18
R:103
G: 23
B: 16
R:106
G: 23
B: 17
R:101
G: 24
B: 18
R: 97
G: 26
B: 20
R: 98
G: 25
B: 18
R: 99
G: 26
B: 19
R:102
G: 25
B: 19
R:102
G: 25
B: 19
R:102
G: 25
B: 17
R:101
G: 24
B: 16
R:104
G: 25
B: 18
R: 98
G: 25
B: 19
R:100
G: 25
B: 19
R:100
G: 25
B: 19
R:102
G: 25
B: 19
R:103
G: 26
B: 20
R:102
G: 23
B: 16
R:103
G: 24
B: 17
R:103
G: 25
B: 15
R: 97
G: 24
B: 18
R:100
G: 25
B: 19
R: 99
G: 24
B: 18
R:102
G: 23
B: 18
R:104
G: 25
B: 20
R:102
G: 23
B: 16
R:103
G: 24
B: 17
R:103
G: 23
B: 16
R: 98
G: 25
B: 19
R: 99
G: 24
B: 19
R: 99
G: 24
B: 19
R:102
G: 23
B: 18
R:103
G: 24
B: 19
R:103
G: 23
B: 16
R:104
G: 24
B: 17
R: 98
G: 27
B: 21
R: 98
G: 25
B: 18
R:100
G: 27
B: 20
R:103
G: 26
B: 20
R:102
G: 25
B: 19
R:104
G: 25
B: 18
R:102
G: 23
B: 16
R:104
G: 25
B: 18
•  Each pixel represents a
measured quantity such
as light
•  A pixel may contain a
scalar number (e.g. for
gray scale images),
triplets of color values
(e.g. RGB), or in general
vectors, matrices and
tensors.
•  Just a bunch of numbers!
Marr’s layers of abstraction (1982)
Primal sketch
Layers of Abstractions
3D Model
2 1/2D sketchDepth
Orientation
Occlusions
Features
Segments
Information reduction by abstraction is
important in computer vision
But what abstractions should we use?
Construct by design or learn from data?
In CV we don’t use the pixels directly,
we use local descriptors often called
features
11
Slide from Anders L. Larsen
Use Artificial Neural Networks to model
Output is class probabilities
y(x;w)
Commercial solutions can do a lot, but …
(e.g. Google Vision API, Amazon Rekognition)
28/01/20 13
Lerbæk herregård
Dansk bondegård
Output from Google Vision API
Bias in public training data: Mainly data from
North America and limited object categories
28/01/20 14
You need huge training datasets
in order to train deep learning
models.
30/01/20 15
Vision is full of hard
problems!
The human visual system is
also challenged
Visual ambiguities:
Multiple correct hypotheses about the scene
30/01/20 16
Humans have a bias when interpreting
scenes – here we have orientation bias
30/01/20 17
Humans have a bias when interpreting
scenes – here we have orientation bias
30/01/20 18
We prefer interpretations we have used before!
And the same holds for a computer vision system!
Choice of training data is important!
Vondrick et al 2013
Do you see the same objects as the computer?
What’s the problem? The representation is not strong enough!
Fine grained classification:
Examples of inter-class proximity
Flowers dataset, Oxford Visual Geometry Group
Fine grained classification:
Examples of large intra-class variation
Caltech-UCSD Birds 200 dataset – North American birds
Photos & film archives: Potential problems
•  Automated meta-data generation:
•  How do we ensure meaningful labeling / meta-data
generation?
•  Potential problems with bias – both geographically (cultural
bias) and temporally (objects change appearance over time).
•  Train on your own data: Where do we get training data labels
from? Manual labor? Crowdsourcing? Other idea?
•  Reading and interpreting text in photos or film might help. This
is a natural language processing problem.
•  Geo-location:
•  Where was this photo taken? Some solutions exist, but does it
work on your data?
•  Search for similar images in archive:
•  There are commercial solutions for this.
28/01/20 22
Summary
•  AI & Computer vision algorithms are getting more and
more advanced and we can solve many hard
problems.
•  However, just as with humans, computer vision
systems can be fooled and do fail.
•  A computer vision system is based on a set of
assumptions – they may be wrong or broken!
•  Learning-based computer vision systems can only be
as good as the training data we use when building the
system. Garbage in = garbage out.
•  Maybe you should join forces and use your combined
archives for improved training and quality of outcome.
28/01/20 23
Questions?
24
Literature
•  LeCun, Bengio, Hinton: Deep learning. Nature review,
Vol. 521: 436 – 444, 2015.
•  Ponti et al.: Everything you wanted to know about
Deep Learning for Computer Vision but were afraid to
ask. Online, 2017.
•  Goodfellow et al.: Deep Learning. MIT Press, 2016.
http://www.deeplearningbook.org
25

Más contenido relacionado

La actualidad más candente

Open CV - 電腦怎麼看世界
Open CV - 電腦怎麼看世界Open CV - 電腦怎麼看世界
Open CV - 電腦怎麼看世界Tech Podcast Night
 
Introduction to computer graphics
Introduction to computer graphicsIntroduction to computer graphics
Introduction to computer graphicsAmandeep Kaur
 
Lecture applications of cg
Lecture   applications of cgLecture   applications of cg
Lecture applications of cgavelraj
 
Computer vision suprim regmi
Computer vision suprim regmi Computer vision suprim regmi
Computer vision suprim regmi Suprim Regmi
 
AI Computer vision
AI Computer visionAI Computer vision
AI Computer visionKashafnaz2
 
Computer vision introduction
Computer vision  introduction Computer vision  introduction
Computer vision introduction Wael Badawy
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine LearningDr. Radhey Shyam
 
computer graphics
computer graphicscomputer graphics
computer graphicsashpri156
 
Computer vision for interactive computer graphics
Computer vision for interactive computer graphicsComputer vision for interactive computer graphics
Computer vision for interactive computer graphicsShah Alam Sabuj
 
Recent Trends in Signal and Image Processing - Applications
Recent Trends in Signal and Image Processing - ApplicationsRecent Trends in Signal and Image Processing - Applications
Recent Trends in Signal and Image Processing - ApplicationsAnand Muglikar
 

La actualidad más candente (20)

Computer Vision
Computer VisionComputer Vision
Computer Vision
 
Computer graphics1
Computer graphics1Computer graphics1
Computer graphics1
 
Computer Vision
Computer VisionComputer Vision
Computer Vision
 
unit-1-intro
 unit-1-intro unit-1-intro
unit-1-intro
 
Computer vision
Computer visionComputer vision
Computer vision
 
Open CV - 電腦怎麼看世界
Open CV - 電腦怎麼看世界Open CV - 電腦怎麼看世界
Open CV - 電腦怎麼看世界
 
Overview of Computer Graphics
Overview of Computer GraphicsOverview of Computer Graphics
Overview of Computer Graphics
 
Introduction Computer Graphic
Introduction Computer GraphicIntroduction Computer Graphic
Introduction Computer Graphic
 
Introduction to computer graphics
Introduction to computer graphicsIntroduction to computer graphics
Introduction to computer graphics
 
Lecture applications of cg
Lecture   applications of cgLecture   applications of cg
Lecture applications of cg
 
Computer vision suprim regmi
Computer vision suprim regmi Computer vision suprim regmi
Computer vision suprim regmi
 
AI Computer vision
AI Computer visionAI Computer vision
AI Computer vision
 
Computer vision
Computer visionComputer vision
Computer vision
 
Computer vision
Computer visionComputer vision
Computer vision
 
Computer vision introduction
Computer vision  introduction Computer vision  introduction
Computer vision introduction
 
Ud 8 presentación ud8
Ud 8  presentación ud8Ud 8  presentación ud8
Ud 8 presentación ud8
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
computer graphics
computer graphicscomputer graphics
computer graphics
 
Computer vision for interactive computer graphics
Computer vision for interactive computer graphicsComputer vision for interactive computer graphics
Computer vision for interactive computer graphics
 
Recent Trends in Signal and Image Processing - Applications
Recent Trends in Signal and Image Processing - ApplicationsRecent Trends in Signal and Image Processing - Applications
Recent Trends in Signal and Image Processing - Applications
 

Similar a Overblik over kunstig intelligens og digital billedanalyse

Digital Image Processing
Digital Image ProcessingDigital Image Processing
Digital Image ProcessingSahil Biswas
 
Overview of computer vision and machine learning
Overview of computer vision and machine learningOverview of computer vision and machine learning
Overview of computer vision and machine learningsmckeever
 
Digital image processing using matlab
Digital image processing using matlab Digital image processing using matlab
Digital image processing using matlab Amr Rashed
 
Face Recognition & Detection Using Image Processing
Face Recognition & Detection Using Image ProcessingFace Recognition & Detection Using Image Processing
Face Recognition & Detection Using Image Processingpaperpublications3
 
Face Recognition & Detection Using Image Processing
Face Recognition & Detection Using Image ProcessingFace Recognition & Detection Using Image Processing
Face Recognition & Detection Using Image Processingpaperpublications3
 
Weeks 1 Introductions_V1_1.ppt
Weeks 1 Introductions_V1_1.pptWeeks 1 Introductions_V1_1.ppt
Weeks 1 Introductions_V1_1.pptssusera0a371
 
Machine Learning ICS 273A
Machine Learning ICS 273AMachine Learning ICS 273A
Machine Learning ICS 273Abutest
 
Big Data & Machine Learning - TDC2013 São Paulo - 12/0713
Big Data & Machine Learning - TDC2013 São Paulo - 12/0713Big Data & Machine Learning - TDC2013 São Paulo - 12/0713
Big Data & Machine Learning - TDC2013 São Paulo - 12/0713Mathieu DESPRIEE
 
Introduction to Machine Vision
Introduction to Machine VisionIntroduction to Machine Vision
Introduction to Machine VisionNasir Jumani
 
Introduction talk to Computer Vision
Introduction talk to Computer Vision Introduction talk to Computer Vision
Introduction talk to Computer Vision Chen Sagiv
 
Big Data & Machine Learning - TDC2013 Sao Paulo
Big Data & Machine Learning - TDC2013 Sao PauloBig Data & Machine Learning - TDC2013 Sao Paulo
Big Data & Machine Learning - TDC2013 Sao PauloOCTO Technology
 
Week2- Deep Learning Intuition.pptx
Week2- Deep Learning Intuition.pptxWeek2- Deep Learning Intuition.pptx
Week2- Deep Learning Intuition.pptxfahmi324663
 
Automatic Image Annotation (AIA)
Automatic Image Annotation (AIA)Automatic Image Annotation (AIA)
Automatic Image Annotation (AIA)Farzaneh Rezaei
 

Similar a Overblik over kunstig intelligens og digital billedanalyse (20)

Digital Image Processing
Digital Image ProcessingDigital Image Processing
Digital Image Processing
 
Overview of computer vision and machine learning
Overview of computer vision and machine learningOverview of computer vision and machine learning
Overview of computer vision and machine learning
 
Lec_1_Introduction.pdf
Lec_1_Introduction.pdfLec_1_Introduction.pdf
Lec_1_Introduction.pdf
 
Lec_1_Introduction.pdf
Lec_1_Introduction.pdfLec_1_Introduction.pdf
Lec_1_Introduction.pdf
 
LR2. Summary Day 2
LR2. Summary Day 2LR2. Summary Day 2
LR2. Summary Day 2
 
DIP-Unit1-Session1.pdf
DIP-Unit1-Session1.pdfDIP-Unit1-Session1.pdf
DIP-Unit1-Session1.pdf
 
Digital image processing using matlab
Digital image processing using matlab Digital image processing using matlab
Digital image processing using matlab
 
Face Recognition & Detection Using Image Processing
Face Recognition & Detection Using Image ProcessingFace Recognition & Detection Using Image Processing
Face Recognition & Detection Using Image Processing
 
Ch1.pptx
Ch1.pptxCh1.pptx
Ch1.pptx
 
Face Recognition & Detection Using Image Processing
Face Recognition & Detection Using Image ProcessingFace Recognition & Detection Using Image Processing
Face Recognition & Detection Using Image Processing
 
Weeks 1 Introductions_V1_1.ppt
Weeks 1 Introductions_V1_1.pptWeeks 1 Introductions_V1_1.ppt
Weeks 1 Introductions_V1_1.ppt
 
Object Recognition
Object RecognitionObject Recognition
Object Recognition
 
Machine Learning ICS 273A
Machine Learning ICS 273AMachine Learning ICS 273A
Machine Learning ICS 273A
 
Big Data & Machine Learning - TDC2013 São Paulo - 12/0713
Big Data & Machine Learning - TDC2013 São Paulo - 12/0713Big Data & Machine Learning - TDC2013 São Paulo - 12/0713
Big Data & Machine Learning - TDC2013 São Paulo - 12/0713
 
Introduction to Machine Vision
Introduction to Machine VisionIntroduction to Machine Vision
Introduction to Machine Vision
 
Introduction talk to Computer Vision
Introduction talk to Computer Vision Introduction talk to Computer Vision
Introduction talk to Computer Vision
 
Big Data & Machine Learning - TDC2013 Sao Paulo
Big Data & Machine Learning - TDC2013 Sao PauloBig Data & Machine Learning - TDC2013 Sao Paulo
Big Data & Machine Learning - TDC2013 Sao Paulo
 
Week2- Deep Learning Intuition.pptx
Week2- Deep Learning Intuition.pptxWeek2- Deep Learning Intuition.pptx
Week2- Deep Learning Intuition.pptx
 
Automatic Image Annotation (AIA)
Automatic Image Annotation (AIA)Automatic Image Annotation (AIA)
Automatic Image Annotation (AIA)
 
ICS1020 CV
ICS1020 CVICS1020 CV
ICS1020 CV
 

Más de LFF - Landsforeningen til bevaring af foto og film

Más de LFF - Landsforeningen til bevaring af foto og film (20)

LFF vinterseminar 2024
LFF vinterseminar 2024LFF vinterseminar 2024
LFF vinterseminar 2024
 
LFF vinterseminar 2024
LFF vinterseminar 2024LFF vinterseminar 2024
LFF vinterseminar 2024
 
LFF vinterseminar 2024
LFF vinterseminar 2024LFF vinterseminar 2024
LFF vinterseminar 2024
 
LFF vinterseminar 2024
LFF vinterseminar 2024LFF vinterseminar 2024
LFF vinterseminar 2024
 
LFF
LFFLFF
LFF
 
LFF vinterseminar 2024
LFF vinterseminar 2024LFF vinterseminar 2024
LFF vinterseminar 2024
 
Erindringsbio
Erindringsbio Erindringsbio
Erindringsbio
 
Hvordan har fortiden set ud på film? Hvordan har virkeligheden set ud?
Hvordan har fortiden set ud på film? Hvordan har virkeligheden set ud?Hvordan har fortiden set ud på film? Hvordan har virkeligheden set ud?
Hvordan har fortiden set ud på film? Hvordan har virkeligheden set ud?
 
Hverdagsfotos og ”rapid response”: Indsamling af fotos under coronapande...
    Hverdagsfotos og ”rapid response”:  Indsamling af fotos under coronapande...    Hverdagsfotos og ”rapid response”:  Indsamling af fotos under coronapande...
Hverdagsfotos og ”rapid response”: Indsamling af fotos under coronapande...
 
Family Living - The True Story
Family Living - The True StoryFamily Living - The True Story
Family Living - The True Story
 
Hverdagens familiebillede i et historisk og nutidigt perspektiv
Hverdagens familiebillede i et historisk og nutidigt perspektivHverdagens familiebillede i et historisk og nutidigt perspektiv
Hverdagens familiebillede i et historisk og nutidigt perspektiv
 
Zahra Mousavi, front-end udvikler & Mette Kia Krabbe Meyer, seniorforsker, D...
 Zahra Mousavi, front-end udvikler & Mette Kia Krabbe Meyer, seniorforsker, D... Zahra Mousavi, front-end udvikler & Mette Kia Krabbe Meyer, seniorforsker, D...
Zahra Mousavi, front-end udvikler & Mette Kia Krabbe Meyer, seniorforsker, D...
 
Arran Rees, Lacking in context: cataloguing experiments with AI and photography
Arran Rees,  Lacking in context: cataloguing experiments with AI and photographyArran Rees,  Lacking in context: cataloguing experiments with AI and photography
Arran Rees, Lacking in context: cataloguing experiments with AI and photography
 
Anton Stonor: Machine learning i arbejdet med SMKs nye onlinesamling
Anton Stonor: Machine learning i arbejdet med SMKs nye onlinesamlingAnton Stonor: Machine learning i arbejdet med SMKs nye onlinesamling
Anton Stonor: Machine learning i arbejdet med SMKs nye onlinesamling
 
Hvordan starter man et frivilligdrevet digitaliseringsværksted? Og hvad sker...
 Hvordan starter man et frivilligdrevet digitaliseringsværksted? Og hvad sker... Hvordan starter man et frivilligdrevet digitaliseringsværksted? Og hvad sker...
Hvordan starter man et frivilligdrevet digitaliseringsværksted? Og hvad sker...
 
ABA AV samling
ABA AV samlingABA AV samling
ABA AV samling
 
Digitalisering i Odense
Digitalisering i OdenseDigitalisering i Odense
Digitalisering i Odense
 
Anvendelse af digitaliseret filmmateriale som kilder.
 Anvendelse af digitaliseret filmmateriale som kilder. Anvendelse af digitaliseret filmmateriale som kilder.
Anvendelse af digitaliseret filmmateriale som kilder.
 
Giv filmen det rigtige efterliv, filmevaring
Giv filmen det rigtige efterliv, filmevaring Giv filmen det rigtige efterliv, filmevaring
Giv filmen det rigtige efterliv, filmevaring
 
LFF sommerseminar 2019
LFF sommerseminar 2019LFF sommerseminar 2019
LFF sommerseminar 2019
 

Último

Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service AvailableCall Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service AvailableSeo
 
Completed Event Presentation for Huma 1305
Completed Event Presentation for Huma 1305Completed Event Presentation for Huma 1305
Completed Event Presentation for Huma 1305jazlynjacobs51
 
8377087607, Door Step Call Girls In Kalkaji (Locanto) 24/7 Available
8377087607, Door Step Call Girls In Kalkaji (Locanto) 24/7 Available8377087607, Door Step Call Girls In Kalkaji (Locanto) 24/7 Available
8377087607, Door Step Call Girls In Kalkaji (Locanto) 24/7 Availabledollysharma2066
 
Mayiladuthurai Call Girls 8617697112 Short 3000 Night 8000 Best call girls Se...
Mayiladuthurai Call Girls 8617697112 Short 3000 Night 8000 Best call girls Se...Mayiladuthurai Call Girls 8617697112 Short 3000 Night 8000 Best call girls Se...
Mayiladuthurai Call Girls 8617697112 Short 3000 Night 8000 Best call girls Se...Nitya salvi
 
Moradabad Call Girls - 📞 8617697112 🔝 Top Class Call Girls Service Available
Moradabad Call Girls - 📞 8617697112 🔝 Top Class Call Girls Service AvailableMoradabad Call Girls - 📞 8617697112 🔝 Top Class Call Girls Service Available
Moradabad Call Girls - 📞 8617697112 🔝 Top Class Call Girls Service AvailableNitya salvi
 
Van Gogh Powerpoint for art lesson today
Van Gogh Powerpoint for art lesson todayVan Gogh Powerpoint for art lesson today
Van Gogh Powerpoint for art lesson todaylucygibson17
 
FULL NIGHT — 9999894380 Call Girls In New Ashok Nagar | Delhi
FULL NIGHT — 9999894380 Call Girls In New Ashok Nagar | DelhiFULL NIGHT — 9999894380 Call Girls In New Ashok Nagar | Delhi
FULL NIGHT — 9999894380 Call Girls In New Ashok Nagar | DelhiSaketCallGirlsCallUs
 
FULL NIGHT — 9999894380 Call Girls In Jasola Vihar | Delhi
FULL NIGHT — 9999894380 Call Girls In Jasola Vihar | DelhiFULL NIGHT — 9999894380 Call Girls In Jasola Vihar | Delhi
FULL NIGHT — 9999894380 Call Girls In Jasola Vihar | DelhiSaketCallGirlsCallUs
 
(9711106444 )🫦#Sexy Desi Call Girls Noida Sector 4 Escorts Service Delhi 🫶
(9711106444 )🫦#Sexy Desi Call Girls Noida Sector 4 Escorts Service Delhi 🫶(9711106444 )🫦#Sexy Desi Call Girls Noida Sector 4 Escorts Service Delhi 🫶
(9711106444 )🫦#Sexy Desi Call Girls Noida Sector 4 Escorts Service Delhi 🫶delhimunirka444
 
FULL NIGHT — 9999894380 Call Girls In Dwarka Mor | Delhi
FULL NIGHT — 9999894380 Call Girls In Dwarka Mor | DelhiFULL NIGHT — 9999894380 Call Girls In Dwarka Mor | Delhi
FULL NIGHT — 9999894380 Call Girls In Dwarka Mor | DelhiSaketCallGirlsCallUs
 
FULL NIGHT — 9999894380 Call Girls In Uttam Nagar | Delhi
FULL NIGHT — 9999894380 Call Girls In Uttam Nagar | DelhiFULL NIGHT — 9999894380 Call Girls In Uttam Nagar | Delhi
FULL NIGHT — 9999894380 Call Girls In Uttam Nagar | DelhiSaketCallGirlsCallUs
 
Call Girls in Sakinaka 9892124323, Vashi CAll Girls Call girls Services, Che...
Call Girls in Sakinaka  9892124323, Vashi CAll Girls Call girls Services, Che...Call Girls in Sakinaka  9892124323, Vashi CAll Girls Call girls Services, Che...
Call Girls in Sakinaka 9892124323, Vashi CAll Girls Call girls Services, Che...Pooja Nehwal
 
FULL NIGHT — 9999894380 Call Girls In Najafgarh | Delhi
FULL NIGHT — 9999894380 Call Girls In Najafgarh | DelhiFULL NIGHT — 9999894380 Call Girls In Najafgarh | Delhi
FULL NIGHT — 9999894380 Call Girls In Najafgarh | DelhiSaketCallGirlsCallUs
 
Editorial sephora annual report design project
Editorial sephora annual report design projectEditorial sephora annual report design project
Editorial sephora annual report design projecttbatkhuu1
 
Akbar Religious Policy and Sufism comparison.pptx
Akbar Religious Policy and Sufism comparison.pptxAkbar Religious Policy and Sufism comparison.pptx
Akbar Religious Policy and Sufism comparison.pptxAmita Gupta
 
FULL NIGHT — 9999894380 Call Girls In Delhi | Delhi
FULL NIGHT — 9999894380 Call Girls In Delhi | DelhiFULL NIGHT — 9999894380 Call Girls In Delhi | Delhi
FULL NIGHT — 9999894380 Call Girls In Delhi | DelhiSaketCallGirlsCallUs
 
THE ARTS OF THE PHILIPPINE BALLET PRESN
THE ARTS OF  THE PHILIPPINE BALLET PRESNTHE ARTS OF  THE PHILIPPINE BALLET PRESN
THE ARTS OF THE PHILIPPINE BALLET PRESNAlvinFerdinandAceCas
 

Último (20)

Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service AvailableCall Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
 
Completed Event Presentation for Huma 1305
Completed Event Presentation for Huma 1305Completed Event Presentation for Huma 1305
Completed Event Presentation for Huma 1305
 
8377087607, Door Step Call Girls In Kalkaji (Locanto) 24/7 Available
8377087607, Door Step Call Girls In Kalkaji (Locanto) 24/7 Available8377087607, Door Step Call Girls In Kalkaji (Locanto) 24/7 Available
8377087607, Door Step Call Girls In Kalkaji (Locanto) 24/7 Available
 
Mayiladuthurai Call Girls 8617697112 Short 3000 Night 8000 Best call girls Se...
Mayiladuthurai Call Girls 8617697112 Short 3000 Night 8000 Best call girls Se...Mayiladuthurai Call Girls 8617697112 Short 3000 Night 8000 Best call girls Se...
Mayiladuthurai Call Girls 8617697112 Short 3000 Night 8000 Best call girls Se...
 
Moradabad Call Girls - 📞 8617697112 🔝 Top Class Call Girls Service Available
Moradabad Call Girls - 📞 8617697112 🔝 Top Class Call Girls Service AvailableMoradabad Call Girls - 📞 8617697112 🔝 Top Class Call Girls Service Available
Moradabad Call Girls - 📞 8617697112 🔝 Top Class Call Girls Service Available
 
Van Gogh Powerpoint for art lesson today
Van Gogh Powerpoint for art lesson todayVan Gogh Powerpoint for art lesson today
Van Gogh Powerpoint for art lesson today
 
FULL NIGHT — 9999894380 Call Girls In New Ashok Nagar | Delhi
FULL NIGHT — 9999894380 Call Girls In New Ashok Nagar | DelhiFULL NIGHT — 9999894380 Call Girls In New Ashok Nagar | Delhi
FULL NIGHT — 9999894380 Call Girls In New Ashok Nagar | Delhi
 
FULL NIGHT — 9999894380 Call Girls In Jasola Vihar | Delhi
FULL NIGHT — 9999894380 Call Girls In Jasola Vihar | DelhiFULL NIGHT — 9999894380 Call Girls In Jasola Vihar | Delhi
FULL NIGHT — 9999894380 Call Girls In Jasola Vihar | Delhi
 
(9711106444 )🫦#Sexy Desi Call Girls Noida Sector 4 Escorts Service Delhi 🫶
(9711106444 )🫦#Sexy Desi Call Girls Noida Sector 4 Escorts Service Delhi 🫶(9711106444 )🫦#Sexy Desi Call Girls Noida Sector 4 Escorts Service Delhi 🫶
(9711106444 )🫦#Sexy Desi Call Girls Noida Sector 4 Escorts Service Delhi 🫶
 
FULL NIGHT — 9999894380 Call Girls In Dwarka Mor | Delhi
FULL NIGHT — 9999894380 Call Girls In Dwarka Mor | DelhiFULL NIGHT — 9999894380 Call Girls In Dwarka Mor | Delhi
FULL NIGHT — 9999894380 Call Girls In Dwarka Mor | Delhi
 
FULL NIGHT — 9999894380 Call Girls In Uttam Nagar | Delhi
FULL NIGHT — 9999894380 Call Girls In Uttam Nagar | DelhiFULL NIGHT — 9999894380 Call Girls In Uttam Nagar | Delhi
FULL NIGHT — 9999894380 Call Girls In Uttam Nagar | Delhi
 
Call Girls in Sakinaka 9892124323, Vashi CAll Girls Call girls Services, Che...
Call Girls in Sakinaka  9892124323, Vashi CAll Girls Call girls Services, Che...Call Girls in Sakinaka  9892124323, Vashi CAll Girls Call girls Services, Che...
Call Girls in Sakinaka 9892124323, Vashi CAll Girls Call girls Services, Che...
 
FULL NIGHT — 9999894380 Call Girls In Najafgarh | Delhi
FULL NIGHT — 9999894380 Call Girls In Najafgarh | DelhiFULL NIGHT — 9999894380 Call Girls In Najafgarh | Delhi
FULL NIGHT — 9999894380 Call Girls In Najafgarh | Delhi
 
(INDIRA) Call Girl Dehradun Call Now 8617697112 Dehradun Escorts 24x7
(INDIRA) Call Girl Dehradun Call Now 8617697112 Dehradun Escorts 24x7(INDIRA) Call Girl Dehradun Call Now 8617697112 Dehradun Escorts 24x7
(INDIRA) Call Girl Dehradun Call Now 8617697112 Dehradun Escorts 24x7
 
UAE Call Girls # 971526940039 # Independent Call Girls In Dubai # (UAE)
UAE Call Girls # 971526940039 # Independent Call Girls In Dubai # (UAE)UAE Call Girls # 971526940039 # Independent Call Girls In Dubai # (UAE)
UAE Call Girls # 971526940039 # Independent Call Girls In Dubai # (UAE)
 
Editorial sephora annual report design project
Editorial sephora annual report design projectEditorial sephora annual report design project
Editorial sephora annual report design project
 
Akbar Religious Policy and Sufism comparison.pptx
Akbar Religious Policy and Sufism comparison.pptxAkbar Religious Policy and Sufism comparison.pptx
Akbar Religious Policy and Sufism comparison.pptx
 
FULL NIGHT — 9999894380 Call Girls In Delhi | Delhi
FULL NIGHT — 9999894380 Call Girls In Delhi | DelhiFULL NIGHT — 9999894380 Call Girls In Delhi | Delhi
FULL NIGHT — 9999894380 Call Girls In Delhi | Delhi
 
THE ARTS OF THE PHILIPPINE BALLET PRESN
THE ARTS OF  THE PHILIPPINE BALLET PRESNTHE ARTS OF  THE PHILIPPINE BALLET PRESN
THE ARTS OF THE PHILIPPINE BALLET PRESN
 
Dubai Call Girl Number # 0522916705 # Call Girl Number In Dubai # (UAE)
Dubai Call Girl Number # 0522916705 # Call Girl Number In Dubai # (UAE)Dubai Call Girl Number # 0522916705 # Call Girl Number In Dubai # (UAE)
Dubai Call Girl Number # 0522916705 # Call Girl Number In Dubai # (UAE)
 

Overblik over kunstig intelligens og digital billedanalyse

  • 1. 30/01/20 1 Kim Steenstrup Pedersen Associate Professor, Ph.D. Head of IMAGE Section Dept. of Computer Science The pros and cons of modern AI & computer vision
  • 2. What is modern Artificial Intelligence (AI)? 30/01/20 2 Machine Learning Bioinformatics Information Retrieval Medical Image Analysis Audio / Speech Analysis And more … Computer Vision Natural Language Processing I am here Robotics Oxford Dict. Def.: The theory and development of computer systems able to perform tasks normally requiring human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages. There is no clear definition (that all agrees upon) of what AI is!
  • 3. What is machine learning? 30/01/20 3 Data is represented as points x in some high dimensional space. Learn = Estimate a function (model) that groups / separate items in this space. y(x;w) ! Apple,Pear{ } A classification problem with two classes
  • 4. •  We need data in order to learn the function / parameters. •  We call this training data and we also talk about validation and test data. •  Approaches to machine learning: •  Supervised learning: We have training data examples of both the input and wanted output •  Unsupervised learning: We only have training data examples of the input •  And combinations thereof: Semi-supervised, active learning, reinforcement learning, … What is machine learning? 30/01/20 4 x1= , y1=Apple x2= , y2=Pear x3= , y3=Pear x1= , y1=? x2= , y2=? x3= , y3=?
  • 5. What is machine learning? 30/01/20 5 The goal is to make as few mistakes on the training set as possible and to make good predictions on new unseen data (test data) y(x;w) ! Apple,Pear{ } ?
  • 6. What is Computer Vision? My definition: The design of algorithms for interpreting visual data by mimicking (and surpassing) the human visual perceptual system.
  • 7. Computer Vision 30/01/20 7 Railroad asset mapping: Detection of signals, signs, cabinets etc. Articulated tracking of humans Some research highlights: Digital natural history: Specimen detection, species recognition, automatic label reading
  • 8. Object recognition and detection What is in this image? “Car” “Window” “Lamp post” Where?“a car” or “street scene” Recognition: Detection:
  • 9. How do we represent an image in the computer? R:101 G: 24 B: 18 R:100 G: 23 B: 17 R:103 G: 24 B: 17 R:102 G: 23 B: 16 R:104 G: 24 B: 17 R:104 G: 24 B: 17 R:108 G: 25 B: 17 R: 98 G: 23 B: 17 R:101 G: 24 B: 18 R:100 G: 23 B: 17 R:103 G: 24 B: 17 R:102 G: 23 B: 16 R:103 G: 23 B: 16 R:104 G: 24 B: 17 R:107 G: 24 B: 16 R: 98 G: 23 B: 17 R:102 G: 25 B: 19 R:101 G: 24 B: 18 R:102 G: 23 B: 16 R:103 G: 24 B: 17 R:103 G: 23 B: 16 R:104 G: 24 B: 17 R:109 G: 24 B: 17 :100 : 23 : 15 :102 : 25 : 17 :101 : 24 : 16 :102 : 23 : 16 :104 : 25 : 18 :103 : 23 : 14 :104 : 24 : 15 :108 : 23 : 16 R:104 G: 24 B: 17 R: 98 G: 25 B: 19 R:100 G: 22 B: 18 R:101 G: 23 B: 19 R:104 G: 23 B: 19 R:103 G: 22 B: 18 R:106 G: 23 B: 17 R:105 G: 22 B: 16 R:107 G: 24 B: 18 R:102 G: 25 B: 19 R:101 G: 24 B: 18 R:101 G: 24 B: 18 R:104 G: 25 B: 18 R:101 G: 22 B: 15 R:105 G: 25 B: 18 R:103 G: 23 B: 16 R:106 G: 23 B: 17 R:101 G: 24 B: 18 R: 97 G: 26 B: 20 R: 98 G: 25 B: 18 R: 99 G: 26 B: 19 R:102 G: 25 B: 19 R:102 G: 25 B: 19 R:102 G: 25 B: 17 R:101 G: 24 B: 16 R:104 G: 25 B: 18 R: 98 G: 25 B: 19 R:100 G: 25 B: 19 R:100 G: 25 B: 19 R:102 G: 25 B: 19 R:103 G: 26 B: 20 R:102 G: 23 B: 16 R:103 G: 24 B: 17 R:103 G: 25 B: 15 R: 97 G: 24 B: 18 R:100 G: 25 B: 19 R: 99 G: 24 B: 18 R:102 G: 23 B: 18 R:104 G: 25 B: 20 R:102 G: 23 B: 16 R:103 G: 24 B: 17 R:103 G: 23 B: 16 R: 98 G: 25 B: 19 R: 99 G: 24 B: 19 R: 99 G: 24 B: 19 R:102 G: 23 B: 18 R:103 G: 24 B: 19 R:103 G: 23 B: 16 R:104 G: 24 B: 17 R: 98 G: 27 B: 21 R: 98 G: 25 B: 18 R:100 G: 27 B: 20 R:103 G: 26 B: 20 R:102 G: 25 B: 19 R:104 G: 25 B: 18 R:102 G: 23 B: 16 R:104 G: 25 B: 18 •  Each pixel represents a measured quantity such as light •  A pixel may contain a scalar number (e.g. for gray scale images), triplets of color values (e.g. RGB), or in general vectors, matrices and tensors. •  Just a bunch of numbers!
  • 10. Marr’s layers of abstraction (1982) Primal sketch Layers of Abstractions 3D Model 2 1/2D sketchDepth Orientation Occlusions Features Segments Information reduction by abstraction is important in computer vision But what abstractions should we use? Construct by design or learn from data? In CV we don’t use the pixels directly, we use local descriptors often called features
  • 11. 11 Slide from Anders L. Larsen
  • 12. Use Artificial Neural Networks to model Output is class probabilities y(x;w)
  • 13. Commercial solutions can do a lot, but … (e.g. Google Vision API, Amazon Rekognition) 28/01/20 13 Lerbæk herregård Dansk bondegård Output from Google Vision API
  • 14. Bias in public training data: Mainly data from North America and limited object categories 28/01/20 14 You need huge training datasets in order to train deep learning models.
  • 15. 30/01/20 15 Vision is full of hard problems! The human visual system is also challenged
  • 16. Visual ambiguities: Multiple correct hypotheses about the scene 30/01/20 16
  • 17. Humans have a bias when interpreting scenes – here we have orientation bias 30/01/20 17
  • 18. Humans have a bias when interpreting scenes – here we have orientation bias 30/01/20 18 We prefer interpretations we have used before! And the same holds for a computer vision system! Choice of training data is important!
  • 19. Vondrick et al 2013 Do you see the same objects as the computer? What’s the problem? The representation is not strong enough!
  • 20. Fine grained classification: Examples of inter-class proximity Flowers dataset, Oxford Visual Geometry Group
  • 21. Fine grained classification: Examples of large intra-class variation Caltech-UCSD Birds 200 dataset – North American birds
  • 22. Photos & film archives: Potential problems •  Automated meta-data generation: •  How do we ensure meaningful labeling / meta-data generation? •  Potential problems with bias – both geographically (cultural bias) and temporally (objects change appearance over time). •  Train on your own data: Where do we get training data labels from? Manual labor? Crowdsourcing? Other idea? •  Reading and interpreting text in photos or film might help. This is a natural language processing problem. •  Geo-location: •  Where was this photo taken? Some solutions exist, but does it work on your data? •  Search for similar images in archive: •  There are commercial solutions for this. 28/01/20 22
  • 23. Summary •  AI & Computer vision algorithms are getting more and more advanced and we can solve many hard problems. •  However, just as with humans, computer vision systems can be fooled and do fail. •  A computer vision system is based on a set of assumptions – they may be wrong or broken! •  Learning-based computer vision systems can only be as good as the training data we use when building the system. Garbage in = garbage out. •  Maybe you should join forces and use your combined archives for improved training and quality of outcome. 28/01/20 23
  • 25. Literature •  LeCun, Bengio, Hinton: Deep learning. Nature review, Vol. 521: 436 – 444, 2015. •  Ponti et al.: Everything you wanted to know about Deep Learning for Computer Vision but were afraid to ask. Online, 2017. •  Goodfellow et al.: Deep Learning. MIT Press, 2016. http://www.deeplearningbook.org 25