CSE152, Spr 11
Intro Computer Vision
Recognition III
Introduction to Computer Vision
CSE 152
Lecture 19
CSE152, Spr 11
Intro Computer Vision
Announcements
• HW 4 due Friday
• Final Exam: Tuesday, 6/7 at 8:0011:00
•
CSE152, Spr 11
Intro Computer Vision
CSE Peer Mentoring Program
seeking volunteers
• Was your first quarter at UCSD hard?
• Would you like to help others through this time?
• We are seeking volunteers for a new peer mentoring
program
– Each mentor will work with a few new majors
• just a couple hours per week
– Mentors will be advised by CSE graduate students
– Mentorship will look great on your resume
• Visit this URL to fill out a short form, and we’ll
contact you over the summer:
http://goo.gl/xLAAj
• Questions?
Contact Bill Griswold: [email protected]
CSE152, Spr 11
Intro Computer Vision
Object Recognition: The Problem
Given: A database D of “known” objects and an image I:
1. Determine which (if any) objects in D appear in I
2. Determine the pose (rotation and translation) of the object
Segmentation
(where is it 2D)
Recognition
(what is it)
Pose Est.
(where is it 3D)
WHAT AND WHERE!!!
CSE152, Spr 11
Intro Computer Vision
Sketch of a Pattern Recognition
Architecture
Feature
Extraction
Classification
Image
(window)
Object
Identity
Feature
Vector
CSE152, Spr 11
Intro Computer Vision
Example: Face Detection
• Scan window over image.
• Search over position & scale.
• Classify window as either:
– Face
– Nonface
Classifier
Window
Face
Nonface
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThe Space of Images
• Consider an npixel image to be a point in an n
dimensional space,
x
!
R
n
.
• Each pixel value is a coordinate of
x
.
x
1
x
2
x
n
x
1
x
n
x
2
CSE152
Computer Vision I
Appearancebased (Viewbased)
•
Face Space:
– A set of face images construct a
face space
in
R
n
– Appearancebased methods analyze the distributions of
individual faces in face space
Some questions:
1. How are images of an individual, under all conditions,
distributed in this space?
2. How are the images of all individuals distributed in this space?
CSE152, Spr 11
Intro Computer Vision
Nearest Neighbor Classifier
x
1
x
2
x
3
ID
=
argmin
j
dist
(
R
j
,
I
)
CSE152
Computer Vision I
An idea:
Represent the set of images as a linear subspace
What is a linear subspace?
Let
V
be a vector space and let
W
be a subset
of
V
. Then
W
is a subspace iff:
1.
The zero vector,
0
, is in
W
.
2.
If
u
and
v
are elements of
W
, then any
linear combination of
u
and
v
is an
element of
W
; a
u
+ b
v
!
W
3.
If
u
is an element of
W
and
c
is a scalar
from
K
, then the scalar product
c
u
!
W
A
d
dimensional subspace is spanned by
d
linearly independent vectors
It is spanned by a ddimensional
orthogonal basis.
Example: A 2D linear
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '08
 staff
 Linear Algebra, Singular value decomposition, SPR

Click to edit the document details