Making a Machine That Sees Like Us by Zygmunt PizloMaking a Machine That Sees Like Us by Zygmunt Pizlo

Making a Machine That Sees Like Us

byZygmunt Pizlo, Yunfeng Li, Tadamasa Sawada

Hardcover | April 16, 2014

Pricing and Purchase Info


Earn 436 plum® points

Prices and offers may vary in store


In stock online

Ships free on orders over $25

Not available in stores


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 ofseeing 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.
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 ...
Title:Making a Machine That Sees Like UsFormat:HardcoverDimensions:272 pages, 9.25 × 6.12 × 0.98 inPublished:April 16, 2014Publisher:Oxford University PressLanguage:English

The following ISBNs are associated with this title:

ISBN - 10:0199922543

ISBN - 13:9780199922543


Table of Contents

1. How the Stage Was Set When We Began1.1 Introduction1.2 What is this book about?1.3 Analytical and Operational definitions of shape1.4 Shape constancy as a phenomenon (something you can observe)1.5 Complexity makes shape unique1.6 How would the world look if we are wrong?1.7 What had happened in the real world while we were away1.8 Perception viewed as an Inverse Problem1.9 How Bayesian inference can be used for modeling perception1.10 What it means to have a model of vision, and why we need to have one1.11 End of the beginning.2. How This All Got Started2.1 Controversy about shape constancy: 1980 - 19952.2 Events surrounding the 29th European Conference on Visual Perception (ECVP), St. Petersburg, Russia, August 20 - 25, 2006 where we first announced our paradigm shift2.3 The role of constraints in recovering the 3D shapes of polyhedral objects from line-drawings2.4 Events surrounding the 31st European Conference on Visual Perception (ECVP) Utrecht, NL, August 24 - 28, 2008, where we had our first big public confrontation2.5 Monocular 3D shape recovery of both synthetic and real objects3. Symmetry in Vision, Inside and Outside of the Laboratory3.1 Why and how approximate computations make visual analyses fast and perfect: the perception of slanted 2D mirror-symmetrical figures3.2 How human beings perceive 2D mirror-symmetry from perspective images3.3 Why 3D mirror-symmetry is more difficult than 2D symmetry3.4 Updating the Ideal Observer: how human beings perceive 3D mirror-symmetry from perspective images3.5 Important role of Generalized Cones in 3D shape perception: how human beings perceive 3D translational-symmetry from perspective images3.6 Michael Layton's contribution to symmetry in shape perception3.7 Leeuwenberg's attempt to develop a "Structural" explanation of Gestalt phenomena4. Using Symmetry Is Not Simple4.1 What is really going on? Examining the relationship between simplicity and likelihood4.2 Clearly, simplicity is better than likelihood - excluding degenerate views does not eliminate spurious 3D symmetrical interpretations4.3 What goes with what? A new kind of Correspondence Problem4.4 Everything becomes easier once symmetry is viewed as self-similarity: the first working solution of the Symmetry Correspondence Problem5. A Second Veiw Makes 3D Shape Perception Perfect5.1 What we know about binocular vision and how we came to know it5.2 How we worked out the binocular perception of symmetrical 3D shapes5.3 How our new theory of shape perception, based on stereoacuity, accounts for old results5.4 3D movies: what they are, what they want to be, and what it costs5.5 Bayesian model of binocular shape perception5.6 Why we could claim that our model is complete6. Figure-Ground Organization, which Breaks Camouflage in Everyday Life, Permits the Veridical Recovery of a 3D Scene6.1 Estimating the orientation of the ground-plane6.2 How a coarse analysis of the positions and sizes of objects can be made6.3 How a useful top-view representation was produced6.4 Finding objects in the 2D image6.5 Extracting relevant edges, grouping them and establishing symmetry correspondence6.6 What can be done with a spatially-global map of a 3D scene?7. What Made This Possible and What Comes Next?7.1 Five Important conceptual contributions7.2 Three of our technical contributions7.3 Making our machine perceive and predict in dynamical environments7.4 Solving the Figure-Ground Organization Problem with only a single 2D image7.5 Recognizing individual objects by using a fast search of memory.