IntrotoComputerVision
Lecture15
DeviParikh
Research Assistant Professor, TTIC
Research
Assistant
Professor,
TTIC
May20,2010
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
Bag of Words-Introduction to Computer Vision-Lecture 15-Computer Science, Lecture notes of Computer Vision
Bag-of-words, Spatial Information, Spatial Pyramid Matching, Implicit Shape Model, Probabilistic Part-Based Model, Generative Part-Based Models, Pictorial Structure Model, Sparse Representation, 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 / 30
This page cannot be seen from the preview
Don't miss anything!
Related documents
Partial preview of the text
Download Bag of Words-Introduction to Computer Vision-Lecture 15-Computer Science and more Lecture notes Computer Vision in PDF only on Docsity!
Intro
to
Computer
Vision
Lecture
Devi
Parikh
Research Assistant Professor, TTICResearch
Assistant
Professor,
TTIC
May
Last timeLast
time
•^ Given a set of training imagesGiven
a^ set
of^
training
images
•^ Can
classify
a^ new
test
image
d^
i
•^ Two
descriptors:
-^ Bag
‐of‐
words
(objects)
-^ Gist
(scenes)
Adding spatial informationAdding
spatial
information
- Spatial
Pyramid
Matching:
Spat a
y a
d
atc
g:
- Computing
bags
of^ features
on^
sub
‐windows
of^ the
whole
image
- Implicit
Shape
Model:
- Using
features
(vocabulary)
to^ vote
for^
object
position
- Probabilistic
Part
‐based
Model:
- Explicit
shape
mode Many^ slides
adapted
from^ Svetlana
Lazebnik,
Fei‐Fei Li,
Rob^ Fergus,
and^ Antonio
Torralba
Spatial Pyramid MatchingSpatial
Pyramid
Matching
Spatial Pyramid MatchingSpatial
Pyramid
Matching
Spatial Pyramid MatchingSpatial
Pyramid
Matching
Spatial Pyramid MatchingSpatial
Pyramid
Matching
Spatial Pyramid MatchingSpatial
Pyramid
Matching
Implicit Shape ModelImplicit
Shape
Model
Implicit shape modelsImplicit
shape
models
•^ Visual codebook is used to index votes for•^ Visual
codebook
is^ used
to^
index
votes
for
object
position
visual
codeword
with
displacement vectors
training
image
annotated
with^
object
localization
info
displacement
vectors
Implicit shape models: DetailsImplicit
shape
models:
Details
Probabilistic Part
‐based Model
Probabilistic
Part
based
Model
Probabilistic
model
max
objecth p objecth shapep objecth
appearanceP
object shape
appearanceP
object imageP
h
= h: assignment
of^ features
to^ parts
Partdescriptors
Partlocations
Candidate
parts
Probabilistic
model
max
objecth p objecth shapep objecth
appearanceP
object shape
appearanceP
object imageP
h
= h: assignment
of^ features
to^ parts^ Part
1
Part 3Part^3
Part^2