Making a Machine That Sees Like Us

by Zygmunt Pizlo, Yunfeng Li, Tadamasa Sawada, Robert M. Steinman

Overview

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.

Product Details

ISBN-13:	9780199922543
Publisher:	Oxford University Press
Publication date:	05/07/2014
Edition description:	New Edition
Pages:	256
Product dimensions:	6.00(w) x 9.30(h) x 0.70(d)

About the Author

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 the Graduate Center for Vision Research at SUNY College of Optometry. He has received his Ph.D. from the Tokyo Institute of Technology in 2006 and had worked as a postdoctoral researcher at Purdue University (2006-2013) and at the Ohio State University (2013-2014). He has been studying human visual perception using psychophysical experiments as well as mathematical and computational modeling.

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.

Table of Contents

Making a Machine That Sees Like Us

1. How the Stage Was Set When We Began

1.1 Introduction
1.2 What is this book about?
1.3 Analytical and Operational definitions of shape
1.4 Shape constancy as a phenomenon (something you can observe)
1.5 Complexity makes shape unique
1.6 How would the world look if we are wrong?
1.7 What had happened in the real world while we were away
1.8 Perception viewed as an Inverse Problem
1.9 How Bayesian inference can be used for modeling perception
1.10 What it means to have a model of vision, and why we need to have one
1.11 End of the beginning.

2. How This All Got Started

2.1 Controversy about shape constancy: 1980 - 1995
2.2 Events surrounding the 29th European Conference on Visual Perception (ECVP), St. Petersburg, Russia, August 20 - 25, 2006 where we first announced our paradigm shift
2.3 The role of constraints in recovering the 3D shapes of polyhedral objects from line-drawings
2.4 Events surrounding the 31st European Conference on Visual Perception (ECVP) Utrecht, NL, August 24 - 28, 2008, where we had our first big public confrontation
2.5 Monocular 3D shape recovery of both synthetic and real objects

3. Symmetry in Vision, Inside and Outside of the Laboratory

3.1 Why and how approximate computations make visual analyses fast and perfect: the perception of slanted 2D mirror-symmetrical figures
3.2 How human beings perceive 2D mirror-symmetry from perspective images
3.3 Why 3D mirror-symmetry is more difficult than 2D symmetry
3.4 Updating the Ideal Observer: how human beings perceive 3D mirror-symmetry from perspective images
3.5 Important role of Generalized Cones in 3D shape perception: how human beings perceive 3D translational-symmetry from perspective images
3.6 Michael Layton's contribution to symmetry in shape perception
3.7 Leeuwenberg's attempt to develop a "Structural" explanation of Gestalt phenomena

4. Using Symmetry Is Not Simple

4.1 What is really going on? Examining the relationship between simplicity and likelihood
4.2 Clearly, simplicity is better than likelihood - excluding degenerate views does not eliminate spurious 3D symmetrical interpretations
4.3 What goes with what? A new kind of Correspondence Problem
4.4 Everything becomes easier once symmetry is viewed as self-similarity: the first working solution of the Symmetry Correspondence Problem

5. A Second View Makes 3D Shape Perception Perfect

5.1 What we know about binocular vision and how we came to know it
5.2 How we worked out the binocular perception of symmetrical 3D shapes
5.3 How our new theory of shape perception, based on stereoacuity, accounts for old results
5.4 3D movies: what they are, what they want to be, and what it costs
5.5 Bayesian model of binocular shape perception
5.6 Why we could claim that our model is complete

6. Figure-Ground Organization, which Breaks Camouflage in Everyday Life, Permits the Veridical Recovery of a 3D Scene

6.1 Estimating the orientation of the ground-plane
6.2 How a coarse analysis of the positions and sizes of objects can be made
6.3 How a useful top-view representation was produced
6.4 Finding objects in the 2D image
6.5 Extracting relevant edges, grouping them and establishing symmetry correspondence
6.6 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 contributions
7.2 Three of our technical contributions
7.3 Making our machine perceive and predict in dynamical environments
7.4 Solving the Figure-Ground Organization Problem with only a single 2D image
7.5 Recognizing individual objects by using a fast search of memory.

Editorial Reviews

"Written in a conversational manner, the book outlines in a step-by-step fashion the rationale for the model and some important ways in which the model differs from other contemporary computational approaches. Making a Machine That Sees Like Us is an important book for anyone with an interest in machine vision for it offers a bottom-up approach to object perception that incorporates a priori constraints rather than sensory data alone. No doubt the inclusion of sensory data together with the constraints is the determining factor in its success as a model of machine vision. It is written in a style that is easy to read by those who do not have much background in visual perception." —PsycCRITIQUES

"This book is timely, interesting, even provocative, and well worth reading. It is especially likely to be of considerable interest to the mathematical psychology community because vision has always enjoyed a special status in the field." —Journal of Mathematical Psychology

From the Publisher