Perceptual Organization for Artificial Vision Systems

by Boyer, Kim L.; Sarkar, Sudeep

• ISBN13: 9780792377993
• ISBN10: 0792377990
• eBook ISBN(s): 9781461544135
• Format: Hardcover
• Copyright: 2000-03-01
• Publisher: Kluwer Academic Pub

Summary

Perceptual Organization for Artificial Vision Systems is an edited collection of invited contributions based on papers presented at The Workshop on Perceptual Organization in Computer Vision, held in Corfu, Greece, in September 1999. The theme of the workshop was 'Assessing the State of the Community and Charting New Research Directions.' Perceptual organization can be defined as the ability to impose structural regularity on sensory data, so as to group sensory primitives arising from a common underlying cause. This book explores new models, theories, and algorithms for perceptual organization. Perceptual Organization for Artificial Vision Systems includes contributions by the world's leading researchers in the field. It explores new models, theories, and algorithms for perceptual organization, as well as demonstrates the means for bringing research results and theoretical principles to fruition in the construction of computer vision systems. The focus of this collection is on the design of artificial vision systems. The chapters comprise contributions from researchers in both computer vision and human vision.

Table of Contents

Contributing Authors	xi
Introduction	1	(16)
Kim L. Boyer
Sudeep Sarkar
Introduction	1	(3)
The Breakout Reports	4	(3)
A Snapshot: Issues from the Floor	7	(2)
Research Contributions: Perceptual Psychology meets Computer Vision	9	(2)
Conclusions and Recommendations	11	(6)
Part I Focused Deliberations
Principles and Methods	17	(12)
David Jacobs
Jitendra Malik
Ram Nevatia
Introduction	17	(1)
Goals of perceptual organization	18	(2)
State of the art	20	(2)
Future directions	22	(7)
Learning and Perceptual Organization	29	(4)
Eric Saund
Jonas August
Joachim Buhmann
Daniel Crevier
Greet Frederix
Danny Roobaert
Introduction	29	(1)
What is there to learn in PO?	30	(1)
Common Perceptual Organization Engine	30	(1)
Training Data	31	(1)
Why is learning important?	32	(1)
Spatiotemporal Grouping	33	(8)
Kim L. Boyer
Daniel Fagerstrom
Michael Kubovy
Peter Johansen
Sudeep Sarkar
Introduction	33	(1)
Three Basic Paradigms	34	(2)
The Questions	36	(1)
Conclusions and Recommendations	37	(4)
Part II Discourses in Human and Machine Vision
Gestalt: From Phenomena to Laws	41	(32)
Michael Kubovy
Sergei Gepshtein
Introduction	41	(2)
Grouping by Proximity in Space	43	(6)
Grouping by Proximity and Similarity	49	(5)
Grouping by Proximity in Space-Time	54	(19)
Convexity in Perceptual Completion	73	(18)
Zili Liu
David W. Jacobs
Ronen Basri
Introduction	73	(1)
Computational theories	74	(1)
Psychological theories	75	(1)
The convexity theory	75	(2)
Grouping and depth discrimination	77	(2)
Experiment 1:	79	(4)
Experiment 2	83	(4)
Discussion	87	(4)
A Gestalt Model of Spatial Perception	91	(30)
Steven Lehar
Introduction	92	(2)
The Gestalt Properties of Perception	94	(5)
The Computational Mechanism of Perception	99	(2)
A Gestalt Bubble Model	101	(14)
Brain Anchoring	115	(1)
Conclusion	116	(5)
What Makes Viewpoint Invariant Properties Perceptually Salient?	121	(18)
David Jacobs
Introduction	121	(1)
Viewpoint Invariance in Computational Grouping	122	(1)
Viewpoint Invariance in Points	123	(8)
Other Gestalt properties	131	(1)
Discussion: Why Minimal Features?	132	(7)
Contour and Texture Analysis for Image Segmentation	139	(34)
Jitendra Malik
Serge Belongie
Thomas Leung
Jianbo Shi
Introduction	139	(6)
Filters, Composite Edgels, and Textons	145	(8)
The Normalized Cut Framework	153	(1)
Defining the Weights	154	(7)
Computing the Segmentation	161	(4)
Results	165	(8)
Perceptual Organization for Generic Object Description	173	(18)
R. Nevatia
Introduction	173	(1)
The Role of Perceptual Organization	174	(2)
Saliency of Features	176	(1)
An Approach to Perceptual Organization	177	(2)
Some System Realizations	179	(6)
Combining Evidence, Uncertainty Reasoning and Machine Learning	185	(2)
Conclusions	187	(4)
Toward Richer Labels for Visual Structure	191	(24)
Eric Saund
Introduction	191	(1)
The Strength of Weak Models	192	(2)
Perceptual Organization in Document Images	194	(7)
Perceptual Organization in Posterized Scenes	201	(9)
Conclusion	210	(5)
Tensor Voting	215	(24)
Chi-Keung Tang
Mi-Suen Lee
Gerard Medioni
Introduction	215	(1)
Previous work	216	(2)
Salient inference engine overview	218	(1)
Tensor representation	219	(3)
Tensor communication	222	(3)
Feature extraction	225	(2)
Complexity	227	(1)
Results in 2-D	227	(3)
Results in 3-D	230	(4)
Conclusion	234	(1)
Software Systems	235	(4)
An observation on saliency	239	(10)
Michael Lindenbaum
Alexander Berengolts
Introduction	239	(2)
Probabilistic Saliency	241	(1)
The probabilistic saliency optimization process	242	(3)
Implementation	245	(1)
Conclusion	246	(3)
Closed Curves in the Analysis and Segmentation of Images	249	(16)
K. K. Thornber
L. R. Williams
Motivation	249	(1)
Theory	250	(8)
Results	258	(4)
Conclusion	262	(3)
The curve indicator random field: Curve organization via edge correlation	265	(24)
Jonas August
Steven W. Zucker
Introduction	265	(3)
Overview of Our Probabilistic Model for Curve Organization	268	(1)
The Underlying Curve Field Model	268	(4)
The Oriented Wiener Filter	272	(4)
Validating the Edge Correlation Assumption	276	(10)
Summary	286	(3)
Euler Spiral for Shape Completion	289	(22)
Benjamin B. Kimia
Ilana Frankel
Ana-Maria Popescu
Introduction	290	(6)
Euler's Spiral	296	(3)
Euler's Spiral for Boundary Modeling and Gap Completion	299	(1)
Biarc Construction and Interpolation	300	(4)
Examples	304	(1)
Summary and Discussion	305	(6)
Bayesian Extraction of Collinear Segment Chains from Digital Images	311	(14)
Daniel Crevier
Introduction	311	(2)
Edge Detection and Linking	313	(1)
Deviation Measures	313	(1)
Underlying Accidental Distributions	314	(1)
Prior Accidental Densities of Deviation Measures	315	(1)
Extraction of the Prior Probability of Non-accidental Junctions	316	(1)
Extraction of Non Accidental Junctions	317	(1)
Extraction of Candidate Chains	317	(1)
Validation of Chains	318	(1)
Iterative Procedure	319	(1)
Examples and Conclusion	319	(6)
Object Detection by Multiprimitive Preattentive Perceptual Organization	325	(22)
Pascal Vasseur
El Mustapha Mouaddib
Claude Pegard
Arnaud Dupuis
Introduction	326	(2)
Previous Work	328	(2)
The Multi-primitive Pre-attentive Approach	330	(9)
Experimental Results	339	(4)
Conclusion	343	(4)
Index	347