Atnaujinkite slapukų nuostatas

El. knyga: Making a Machine That Sees Like Us [Oxford Scholarship Online E-books]

(Professor of Psychological Sciences and of Electrical and Computer Engineering, Purdue University, Indianapolis, IN, United States of America), , (P), (Postdoctoral Fellow, Purdue University, West Lafayette, IN, United States of America)
  • Formatas: 256 pages
  • Išleidimo metai: 29-May-2014
  • Leidėjas: Oxford University Press Inc
  • ISBN-13: 9780199922543
Kitos knygos pagal šią temą:
  • Oxford Scholarship Online E-books
  • Kaina nežinoma
Making a Machine That Sees Like UsDidesnis paveikslėlis
  • Formatas: 256 pages
  • Išleidimo metai: 29-May-2014
  • Leidėjas: Oxford University Press Inc
  • ISBN-13: 9780199922543
Kitos knygos pagal šią temą:
Wiley OnlineMore info about Oxford Scholarship Online e-books
Partnerių interneto svetainė: http://www.oxfordscholarship.com/view/10.1093/acprof:oso/9780199922543.001.0001/acprof-9780199922543
Making a Machine That Sees Like Us explains why and how our visual perceptions can provide us with an accurate representation of the external world. Along the way, it tells the story of a machine (a computational model) built by the authors that solves the computationally difficult problem of seeing the way humans do. This accomplishment required a radical paradigm shift - one that challenged preconceptions about visual perception and tested the limits of human behavior-modeling for practical application.

The text balances scientific sophistication and compelling storytelling, making it accessible to both technical and general readers. Online demonstrations and references to the authors' previously published papers detail how the machine was developed and what drove the ideas needed to make it work. The authors contextualize their new theory of shape perception by highlighting criticisms and opposing theories, offering readers a fascinating account not only of their revolutionary results, but of the scientific process that guided the way.
Acknowledgments xi
1 How the stage was set when we began
1(51)
1.1 Introduction
1(1)
1.2 What is this book about?
2(4)
1.3 Analytical and operational definitions of shape
6(9)
1.4 Shape constancy as a phenomenon (something you can observe)
15(8)
1.5 Complexity makes shape unique
23(5)
1.6 How would the world look if we are wrong?
28(8)
1.7 What had happened in the real world while we were away
36(3)
1.8 Perception viewed as an inverse problem
39(4)
1.9 How Bayesian inference can be used for modeling perception
43(3)
1.10 What it means to have a model of vision, and why we need to have one?
46(3)
1.11 End of the beginning
49(3)
2 How this all got started
52(31)
2.1 Controversy about shape constancy: 1980--1995
52(8)
2.2 29th European Conference on Visual Perception (ECVP), St. Petersburg, Russia, August 20--25, 2006, where we first proposed our paradigm shift
60(2)
2.3 The role of constraints in recovering the 3D shapes of polyhedral objects from line-drawings
62(9)
2.4 31st European Conference on Visual Perception (ECVP) Utrecht, NL, August 24--28, 2008, where we had our first public confrontation
71(2)
2.5 Monocular 3D shape recovery of both synthetic and real objects
73(10)
3 Symmetry In vision, Inside and outside of the laboratory
83(37)
3.1 Why and how approximate computations make visual analyses fast and perfect: The perception of slanted 2D mirror-symmetrical figures
85(11)
3.2 How human beings perceive 2D mirror-symmetry from perspective images
96(2)
3.3 Why 3D mirror-symmetry is more difficult than 2D symmetry
98(1)
3.4 Updating the ideal observer: How human beings perceive 3D mirror-symmetry from perspective images
99(6)
3.5 Important role of generalized cones in 3D shape perception: How human beings perceive 3D translational-symmetry from perspective images
105(9)
3.6 Michael Layton's contribution to symmetry in shape perception
114(2)
3.7 Leeuwenberg's attempt to develop a "structural" explanation of Gestalt phenomena
116(4)
4 Using symmetry Is not simple
120(24)
4.1 What is really going on? Examining the relationship between simplicity and likelihood
124(5)
4.2 Clearly, simplicity is better than likelihood---excluding degenerate views does not eliminate spurious 3D symmetrical interpretations
129(1)
4.3 What goes with what? A new kind of correspondence problem
130(6)
4.4 Everything becomes easier once symmetry is viewed as self-similarity: The first working solution of the symmetry correspondence problem
136(8)
5 A second view makes 3D shape perception perfect
144(28)
5.1 What we know about binocular vision and how we came to know it
145(13)
5.2 How we worked out the binocular perception of symmetrical 3D shapes
158(2)
5.3 How our new theory of shape perception, based on stereoacuity, accounts for old results
160(2)
5.4 3D movies: what they are, what they want to be, and what it costs
162(1)
5.5 Bayesian model of binocular shape perception
163(6)
5.6 Why we could claim that our model is complete?
169(3)
6 Figure-ground organization, which breaks camouflage in everyday life, permits the veridical recovery of a 3D scene
172(32)
6.1 Estimating the orientation of the ground-plane
175(4)
6.2 How a coarse analysis of the positions and sizes of objects can be made
179(3)
6.3 How a useful top view representation was produced
182(8)
6.4 Finding objects in the 2D image
190(2)
6.5 Extracting relevant edges, grouping them, and establishing symmetry correspondence
192(6)
6.6 What can be done with a spatially-global map of a 3D scene?
198(6)
7 What made this possible and what comes next?
204(17)
7.1 Five important conceptual contributions
205(4)
7.2 Three of our technical contributions
209(4)
7.3 Making our machine perceive and predict in dynamical environments
213(3)
7.4 Solving the figure-ground organization problem with only a single 2D image
216(2)
7.5 Recognizing individual objects by using a fast search of memory
218(3)
Note Added in Proofs: Symmetry, The Least-Action Principle, and Conservation Laws in Psychology 221(8)
References 229(8)
Index 237
Zygmunt Pizlo is a professor of Psychological Sciences and of Electrical and Computer Engineering at Purdue University. He has published over 100 journal and conference papers on all aspects of vision as well as on problem-solving. In 2008, he published the first book devoted to 3D shape-perception.



Yunfeng Li is a postdoctoral fellow at Purdue University. His research interests focus on applying psychophysics and mathematics to explore and model human visual perception of 3D shapes and scenes, regularization and Bayesian methods, and human and robot visual navigation.

Tadamasa Sawada is a postdoctoral researcher in Department of Psychology at the Ohio State University. He received his Ph.D. from the Tokyo Institute of Technology in 2006 and worked as a postdoctoral researcher at Purdue University between 2006 and 2013.

Robert M. Steinman devoted most of his scientific career, which began in 1964, to sensory and perceptual process, heading this specialty area in the Department of Psychology at the University of Maryland in College Park until his retirement in 2008. Most of his publications, before collaborating on shape perception with Prof. Pizlo, were concerned with human eye movements. Prof. Steinman, with Prof. Azriel Rosenfeld of the Center for Automation Research at UMD, supervised Prof. Pizlo's doctoral degree in Psychology, which was awarded in 1991. Prof. Steinman has been collaborating with Prof. Pizlo in his studies of shape perception since 2000.
Pastovi nuoroda: https://www.kriso.lt/db/9780199922543_pe.html