lecture19 - EECS 442 Computer vision Object Recognition...

Info iconThis preview shows pages 1–27. Sign up to view the full content.

View Full Document Right Arrow Icon
EECS 442 – Computer vision Object Recognition •Intro • Recognition of single 3D objects • Bag of world models • Part based models • Models for 3D objects categorization • Face recognition
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
EECS 442 – Computer vision Object Recognition This segment is based on the tutorial “ Recognizing and Learning Object Categories: Year 2007 ”,by Prof A. Torralba, R. Fergus and F. Li •Intro • Recognition of single 3D objects • Bag of world models • Part based models • Models for 3D objects categorization • Face recognition
Background image of page 2
Bruegel, 1564
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Plato said… • Ordinary objects are classified together if they `participate' in the same abstract Form, such as the Form of a Human or the Form of Quartz. • Forms are proper subjects of philosophical investigation, for they have the highest degree of reality. • Ordinary objects, such as humans, trees, and stones, have a lower degree of reality than the Forms. • Fictions, shadows, and the like have a still lower degree of reality than ordinary objects and so are not proper subjects of philosophical enquiry.
Background image of page 4
How many object categories are there? Biederman 1987
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 6
Challenges: viewpoint variation Michelangelo 1475-1564 slide credit: Fei-Fei, Fergus & Torralba
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Challenges: illumination image credit: J. Koenderink
Background image of page 8
Challenges: scale slide credit: Fei-Fei, Fergus & Torralba
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Challenges: deformation
Background image of page 10
Challenges: occlusion Magritte, 1957 slide credit: Fei-Fei, Fergus & Torralba
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Challenges: background clutter Kilmeny Niland. 1995
Background image of page 12
Challenges: intra-class variation
Background image of page 13

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
History: single object recognition No intra-class variation: single object recognition
Background image of page 14
So what does object recognition involve?
Background image of page 15

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Identification: is that Potala Palace?
Background image of page 16
Detection: are there people?
Background image of page 17

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Object categorization mountain building tree banner vendor people street lamp
Background image of page 18
Scene and context categorization • outdoor •c ity •…
Background image of page 19

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Turk and Pentland, 1991 Belhumeur, Hespanha, & Kriegman, 1997 Schneiderman & Kanade 2004 Viola and Jones, 2000 Amit and Geman, 1999 LeCun et al. 1998 Belongie and Malik, 2002 Schneiderman & Kanade, 2004 Argawal and Roth, 2002 Poggio et al. 1993 Some early works on object categorization
Background image of page 20
Object categorization: Object categorization: the statistical viewpoint the statistical viewpoint ) | ( image zebra p ) ( e zebra|imag no p vs. •Bayesrule: ) | ( ) | ( image zebra no p image zebra p
Background image of page 21

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Object categorization: Object categorization: the statistical viewpoint the statistical viewpoint ) | ( image zebra p ) ( e zebra|imag no p vs. •Bayesrule: ) ( ) ( ) | ( ) | ( ) | ( ) | ( zebra no p zebra p zebra no image p zebra image p image zebra no p image zebra p = posterior ratio likelihood ratio prior ratio
Background image of page 22
Object categorization: Object categorization: the statistical viewpoint the statistical viewpoint •Bayesrule: ) ( ) ( ) | ( ) | ( ) | ( ) | ( zebra no p zebra p zebra no image p zebra image p image zebra no p image zebra p = posterior ratio likelihood ratio prior ratio • Discriminative methods model posterior • Generative methods model likelihood and prior
Background image of page 23

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Three main issues Three main issues • Representation – How to represent an object category •Learning – How to form the classifier, given training data • Recognition – How the classifier is to be used on novel data
Background image of page 24
Representation – Generative / discriminative / hybrid
Background image of page 25

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Representation – Generative / discriminative / hybrid – Appearance only or location and appearance
Background image of page 26
Image of page 27
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 97

lecture19 - EECS 442 Computer vision Object Recognition...

This preview shows document pages 1 - 27. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online