cse 455 computer vision autumn 2010
DESCRIPTION
CSE 455 Computer Vision Autumn 2010. Professor Linda Shapiro [email protected] TA: Alfred Gui [email protected]. Introduction. What IS computer vision? Where do images come from?. The analysis of digital images by a computer. You tell me!. Applications: Medical Imaging. - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/1.jpg)
CSE 455Computer Vision
Autumn 2010
Professor Linda Shapiro
TA: Alfred Gui
1
![Page 2: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/2.jpg)
Introduction
• What IS computer vision?
• Where do images come from?
The analysis of digital images by a computer
2
You tell me!
![Page 3: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/3.jpg)
Applications: Medical Imaging
CT image of apatient’s abdomen
liver
kidney kidney
3
![Page 4: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/4.jpg)
Visible Man Slice Through Lung
4
![Page 5: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/5.jpg)
3D Reconstruction of the Blood Vessel Tree
5
![Page 6: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/6.jpg)
Mouse Eye Image Retrieval for Genetic Studies
6
![Page 7: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/7.jpg)
Robotics• 2D Gray-tone or Color Images
• 3D Range Images
“Mars” rover
What am I?
7
![Page 8: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/8.jpg)
Robot Soccer
8
![Page 9: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/9.jpg)
Image Databases:
Images from my Ground-Truth collection:http://www.cs.washington.edu/research/imagedatabase/groundtruth
• Retrieve images containing trees
9
![Page 10: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/10.jpg)
Original Images Color Regions Texture Regions Line Clusters
Some Features for Image Retrieval
10
![Page 11: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/11.jpg)
Documents:
11
![Page 12: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/12.jpg)
12
![Page 13: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/13.jpg)
Classified as Cal as Dor
Cal 114 72
Dor 70 133
Previous Classification Results:
Yor (Yor)
Classified as Cal as Yor
Cal 171 16
Yor 0 99
CalineuriaCalineuria (Cal) DoroneuriaDoroneuria (Dor)
Science
13UW and Oregon State University
![Page 14: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/14.jpg)
Soil Mesofauna
AchipteriaA BdellozoniumI BelbaA BelbaI CatoposurusA EniochthoniusA
EntomobrgaTM EpidamaeusA EpilohmanniaA EpilohmanniaD EpilohmanniaT HypochthoniusLA
HypogastruraA
IsotomaAIsotomaVI LiacarusRA MetrioppiaA
NothrusF
onychiurusAOppiellaA PeltenuialaA PhthiracarusA
PlatynothrusFPlatynothrusI
PtenothrixV
PtiliidA
QuadroppiaA
SiroVITomocerusA
TraychetesA XenillusA ZyqoribafulaA
![Page 15: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/15.jpg)
Original Video Frame
Structure RegionsColor Regions
Surveillance: Event Recognition in Aerial Videos
15
![Page 16: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/16.jpg)
2D Face Detection
16
![Page 17: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/17.jpg)
17
Face Recognition
Glasgow University
![Page 18: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/18.jpg)
2D Object Recognition from “Parts”
18
Oxford University
![Page 19: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/19.jpg)
Andy Serkis, Gollum, Lord of the Rings
Graphics: Special Effects
19
![Page 20: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/20.jpg)
3D Reconstruction and Graphics Viewer
20
![Page 21: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/21.jpg)
21
3D Craniofacial Shape Analysis from Meshes of Children’s Heads
![Page 22: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/22.jpg)
Digital Image Terminology:
0 0 0 0 1 0 0 0 0 1 1 1 0 0 0 1 95 96 94 93 92 0 0 92 93 93 92 92 0 0 93 93 94 92 93 0 1 92 93 93 93 93 0 0 94 95 95 96 95
pixel (with value 94)
its 3x3 neighborhood
• binary image• gray-scale (or gray-tone) image• color image• multi-spectral image• range image• labeled image
region of medium intensity
resolution (7x7)
22
![Page 23: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/23.jpg)
The Three Stages of Computer Vision
• low-level
• mid-level
• high-level
image image
image features
features analysis
23
![Page 24: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/24.jpg)
Low-Level
blurring
sharpening
24
![Page 25: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/25.jpg)
Low-Level
Canny
ORT
Mid-Level
original image edge image
edge image circular arcs and line segments
datastructure
25
![Page 26: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/26.jpg)
Mid-level
K-meansclustering
original color image regions of homogeneous color
(followed byconnectedcomponentanalysis)
datastructure
26
![Page 27: CSE 455 Computer Vision Autumn 2010](https://reader035.vdocuments.us/reader035/viewer/2022062517/56812ec9550346895d946904/html5/thumbnails/27.jpg)
edge image
consistentline clusters
low-level
mid-level
high-level
Low- to High-Level
Building Recognition27