Perceptual Organization And Visual Recognition

COMPUTER VISION is a field of research that encompasses many objectives. A primary goal has been to construct visual sensors that can provide general-purpose robots with the same information about their surroundings as we receive from our own visual senses. This book takes an important step towards this goal by describing a working computer vision system named SCERPO. This system can recognize known three-dimensional objects in ordinary black-and-white images taken from unknown viewpoints, even when parts of the object are undetectable or hidden from view. A second major goal of computer vision re search is to provide a computational understanding of human vision. The research presented in this book has many implica tions for our understanding of human vision, particularly in the areas of perceptual organization and knowledge-based recogni tion. An attempt has been made to relate each computational result to the relevant areas in the psychology of vision. Since the material is meant to be accessible to a wide range of inter disciplinary readers, the book is written in plain language and attempts to explain most concepts from the starting position of the non-specialist. vii viii PREFACE One of the most important conclusions ansmg from this research is that visual recognition can commonly be achieved directly from the two-dimensional image without any prelim inary reconstruction of depth information or surface orienta tion from the visual input.

This book presents an overview of different frameworks for understanding perceptual organization, and a state-of-the-art summary of the domain. It describes findings from visual search, illusory contours, and object recognition using electrophysiological measures.

From a barrage of photons, we readily and effortlessly recognize the faces of our friends, and the familiar objects and scenes around us. However, these tasks cannot be simple for our visual systems--faces are all extremely similar as visual patterns, and objects look quite different when viewed from different viewpoints. How do our visual systems solve these problems? The contributors to this volume seek to answer this question by exploring how analytic and holistic processes contribute to our perception of faces, objects, and scenes. The role of parts and wholes in perception has been studied for a century, beginning with the debate between Structuralists, who championed the role of elements, and Gestalt psychologists, who argued that the whole was different from the sum of its parts. This is the first volume to focus on the current state of the debate on parts versus wholes as it exists in the field of visual perception by bringing together the views of the leading researchers. Too frequently, researchers work in only one domain, so they are unaware of the ways in which holistic and analytic processing are defined in different areas. The contributors to this volume ask what analytic and holistic processes are like; whether they contribute differently to the perception of faces, objects, and scenes; whether different cognitive and neural mechanisms code holistic and analytic information; whether a single, universal system can be sufficient for visual-information processing, and whether our subjective experience of holistic perception might be nothing more than a compelling illusion. The result is a snapshot of the current thinking on how the processing of wholes and parts contributes to our remarkable ability to recognize faces, objects, and scenes, and an illustration of the diverse conceptions of analytic and holistic processing that currently coexist, and the variety of approaches that have been brought to bear on the issues.

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.

Perceptual organization comprises a wide range of processes such as perceptual grouping, figure-ground organization, filling-in, completion and perceptual switching. 'Oxford Handbook of Perceptual Organization' provides a broad and extensive review of the current literature, written in an accessible form for scholars and students.

An exploration of ideas emanating from behavioural, developmental, neurophysiological, neuropsychological and computational approaches to the problem of visual perceptual organization. It is based on papers presented at the 31st Carnegie Symposium on Cognition, held in June 2000.

This book describes the design of a complete, flexible system for perceptual organization in computer vision using graph theoretic techniques, voting methods, and an extension of the Bayesian networks called perceptual inference networks (PINs). The PIN, which forms the heart of the system and which is based on Bayesian probabilistic networks, exhibits potential for application in several areas of computer vision as well as a range of other spatial reasoning tasks. The text includes a highly comprehensive, classificatory review of prior work in perceptual organization and, within that framework, identifies key areas for future work by the computer vision research community.

Originally published in 1981, perceptual organization had been synonymous with Gestalt psychology, and Gestalt psychology had fallen into disrepute. In the heyday of Behaviorism, the few cognitive psychologists of the time pursued Gestalt phenomena. But in 1981, Cognitive Psychology was married to Information Processing. (Some would say that it was a marriage of convenience.) After the wedding, Cognitive Psychology had come to look like a theoretically wrinkled Behaviorism; very few of the mainstream topics of Cognitive Psychology made explicit contact with Gestalt phenomena. In the background, Cognition's first love – Gestalt – was pining to regain favor. The cognitive psychologists' desire for a phenomenological and intellectual interaction with Gestalt psychology did not manifest itself in their publications, but it did surface often enough at the Psychonomic Society meeting in 1976 for them to remark upon it in one of their conversations. This book, then, is the product of the editors’ curiosity about the status of ideas at the time, first proposed by Gestalt psychologists. For two days in November 1977, they held an exhilarating symposium that was attended by some 20 people, not all of whom are represented in this volume. At the end of our symposium it was agreed that they would try, in contributions to this volume, to convey the speculative and metatheoretical ground of their research in addition to the solid data and carefully wrought theories that are the figure of their research.