IntrotoComputerVision
Lecture14
DeviParikh
Research Assistant Professor, TTIC
Research
Assistant
Professor,
TTIC
May18,2010
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Guidelines and tips
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Community
Ask the community
Ask the community for help and clear up your study doubts
University Rankings
Discover the best universities in your country according to Docsity users
Free resources
Our save-the-student-ebooks!
Download our free guides on studying techniques, anxiety management strategies, and thesis advice from Docsity tutors
Object Categorization-Introduction to Computer Vision-Lecture 14-Computer Science, Lecture notes of Computer Vision
Object Categorization, Context Categorization, Activity, Image Classification, Bag-of-Features, Texture Classification, Texture Recognition, Feature Extraction, Visual Vocabulary, Image Representation, Global Features, Local Features, Gist Descriptor, Scene Perceptual Dimensions, Scene Matching, K-Means Clustering, Greg Shakhnarovich, Lecture Slides, Introduction to Computer Vision, Computer Science, Toyota Technological Institute at Chicago, United States of America.
Typology: Lecture notes
2011/2012
1 / 57
This page cannot be seen from the preview
Don't miss anything!
Related documents
Partial preview of the text
Download Object Categorization-Introduction to Computer Vision-Lecture 14-Computer Science and more Lecture notes Computer Vision in PDF only on Docsity!
Intro^ to^
Computer
Vision
Lecture^
14 Devi Parikh
Research Assistant Professor, TTICResearch^ Assistant
Professor,^
TTIC
May^ 18,^2010
(Some of) What you
’ve learnt so far…
(Some^ of)
What^ you ve
learnt^ so
far…
Pixels^
Corners Edges^
Lines
Verification:
is^ that^ a^ lamp?
Slide^ by^ Fei‐Fei,^ Fergus,^ Torralba
Detection:
are^ there
people?^
Slide^ by^ Fei‐Fei,^ Fergus,
Torralba
Object^ categorization
Slide^ by^ Fei‐Fei,^ Fergus,
Torralba mountain tree
building tree bbanner
street lampstreet^ lamp^ vendor^ vendor people
Scene^ and
context^ categorization
Slide^ by^ Fei‐Fei,^ Fergus,
Torralba
- outdoor• city • …
Today: Image classificationToday:^ Image
classification
Coast^ Highway
Mountain
Street Forest^ I^
id^ it^ O^
t^ T ll b ildi
Scene recognition^
Forest^ Inside
city^ Open^ country
Tall^ buildings
recognition
Aeroplane^
Car‐rear^
Face Ketch^
Motorbike^
Watch
Object recognition
OutlineOutline
-^ ClassificationClassification^ f^
d^ d^ i
-^ Bag‐of‐words
descriptor
-^ Gist^ descriptor
Classification People
Text I Speech
Images
Classification Group A^ Group^
B^ Group
? A A AAA^ area of square (square inches)
?
0.^
BB BB B0.250.10 0.15 0. area^ of^ square^ (square
inches)
ClassificationGroup A Group B
…
Group^ C
……
Group^?
Classification re
‐cap
Classification
re^ cap
-^ Given (item group
) pairs Given^ (item
,group)^ pairs
-^ Construct
a^ representation
to^ describe
the^ an
itemitem • Given^ a^ new
item,^ assign
the^ group^
of^ nearest
i hbneighbor * Just one way to do itJust^ one^ way^ to
do^ it
Bag‐of‐featuresBag^ of^ features Many slides adapted^ from^ Svetlana^ Lazebnik,
Fei‐Fei Li,^ Rob^ Fergus,^ and
Antonio^ Torralba
Origin^ 1:
Texture
classification
-^ Texture^ is
characterized
by^ the^ repetition
of^ basic
elements or
textons elements^ or
textons
-^ It^ is^ the^ identity
of^ the^ textons,
not^ their^ spatial arrangement that mattersarrangement
,^ that^ matters