Object Recognition in Man, Monkey, and Machine


Book Description

The contributors bring a wide range of methodologies to bear on the common problem of image-based object recognition. These interconnected essays on three-dimensional visual object recognition present cutting-edge research by some of the most creative neuroscientific, cognitive, and computational scientists in the field. Cassandra Moore and Patrick Cavanagh take a classic demonstration, the perception of "two-tone" images, and turn it into a method for understanding the nature of object representations in terms of surfaces and the interaction between bottom-up and top-down processes. Michael J. Tarr and Isabel Gauthier use computer graphics to study whether viewpoint-dependent recognition mechanisms can generalize between exemplars of perceptually defined classes. Melvyn A. Goodale and G. Keith Humphrey use innovative psychophysical techniques to investigate dissociable aspects of visual and spatial processing in brain-injured subjects. D.I. Perrett, M.W. Oram, and E. Ashbridge combine neurophysiological single-cell data from monkeys with computational analyses for a new way of thinking about the mechanisms that mediate viewpoint-dependent object recognition and mental rotation. Shimon Ullman also addresses possible mechanisms to account for viewpoint-dependent behavior, but from the perspective of machine vision. Finally, Philippe G. Schyns synthesizes work from many areas, to provide a coherent account of how stimulus class and recognition task interact. The contributors bring a wide range of methodologies to bear on the common problem of image-based object recognition.







How Humans Recognize Objects: Segmentation, Categorization and Individual Identification


Book Description

Human beings experience a world of objects: bounded entities that occupy space and persist through time. Our actions are directed toward objects, and our language describes objects. We categorize objects into kinds that have different typical properties and behaviors. We regard some kinds of objects – each other, for example – as animate agents capable of independent experience and action, while we regard other kinds of objects as inert. We re-identify objects, immediately and without conscious deliberation, after days or even years of non-observation, and often following changes in the features, locations, or contexts of the objects being re-identified. Comparative, developmental and adult observations using a variety of approaches and methods have yielded a detailed understanding of object detection and recognition by the visual system and an advancing understanding of haptic and auditory information processing. Many fundamental questions, however, remain unanswered. What, for example, physically constitutes an “object”? How do specific, classically-characterizable object boundaries emerge from the physical dynamics described by quantum theory, and can this emergence process be described independently of any assumptions regarding the perceptual capabilities of observers? How are visual motion and feature information combined to create object information? How are the object trajectories that indicate persistence to human observers implemented, and how are these trajectory representations bound to feature representations? How, for example, are point-light walkers recognized as single objects? How are conflicts between trajectory-driven and feature-driven identifications of objects resolved, for example in multiple-object tracking situations? Are there separate “what” and “where” processing streams for haptic and auditory perception? Are there haptic and/or auditory equivalents of the visual object file? Are there equivalents of the visual object token? How are object-identification conflicts between different perceptual systems resolved? Is the common assumption that “persistent object” is a fundamental innate category justified? How does the ability to identify and categorize objects relate to the ability to name and describe them using language? How are features that an individual object had in the past but does not have currently represented? How are categorical constraints on how objects move or act represented, and how do such constraints influence categorization and the re-identification of individuals? How do human beings re-identify objects, including each other, as persistent individuals across changes in location, context and features, even after gaps in observation lasting months or years? How do human capabilities for object categorization and re-identification over time relate to those of other species, and how do human infants develop these capabilities? What can modeling approaches such as cognitive robotics tell us about the answers to these questions? Primary research reports, reviews, and hypothesis and theory papers addressing questions relevant to the understanding of perceptual object segmentation, categorization and individual identification at any scale and from any experimental or modeling perspective are solicited for this Research Topic. Papers that review particular sets of issues from multiple disciplinary perspectives or that advance integrative hypotheses or models that take data from multiple experimental approaches into account are especially encouraged.




Object Recognition


Book Description

Automatie object recognition is a multidisciplinary research area using con cepts and tools from mathematics, computing, optics, psychology, pattern recognition, artificial intelligence and various other disciplines. The purpose of this research is to provide a set of coherent paradigms and algorithms for the purpose of designing systems that will ultimately emulate the functions performed by the Human Visual System (HVS). Hence, such systems should have the ability to recognise objects in two or three dimensions independently of their positions, orientations or scales in the image. The HVS is employed for tens of thousands of recognition events each day, ranging from navigation (through the recognition of landmarks or signs), right through to communication (through the recognition of characters or people themselves). Hence, the motivations behind the construction of recognition systems, which have the ability to function in the real world, is unquestionable and would serve industrial (e.g. quality control), military (e.g. automatie target recognition) and community needs (e.g. aiding the visually impaired). Scope, Content and Organisation of this Book This book provides a comprehensive, yet readable foundation to the field of object recognition from which research may be initiated or guided. It repre sents the culmination of research topics that I have either covered personally or in conjunction with my PhD students. These areas include image acqui sition, 3-D object reconstruction, object modelling, and the matching of ob jects, all of which are essential in the construction of an object recognition system.




Visual Object Recognition


Book Description

The visual recognition problem is central to computer vision research. From robotics to information retrieval, many desired applications demand the ability to identify and localize categories, places, and objects. This tutorial overviews computer vision algorithms for visual object recognition and image classification. We introduce primary representations and learning approaches, with an emphasis on recent advances in the field. The target audience consists of researchers or students working in AI, robotics, or vision who would like to understand what methods and representations are available for these problems. This lecture summarizes what is and isn't possible to do reliably today, and overviews key concepts that could be employed in systems requiring visual categorization. Table of Contents: Introduction / Overview: Recognition of Specific Objects / Local Features: Detection and Description / Matching Local Features / Geometric Verification of Matched Features / Example Systems: Specific-Object Recognition / Overview: Recognition of Generic Object Categories / Representations for Object Categories / Generic Object Detection: Finding and Scoring Candidates / Learning Generic Object Category Models / Example Systems: Generic Object Recognition / Other Considerations and Current Challenges / Conclusions




Object Recognition, Attention, and Action


Book Description

Human object recognition is a classical topic both for philosophy and for the natural sciences. Ultimately, understanding of object recognition will be promoted by the cooperation of behavioral research, neurophysiology, and computation. This original book provides an excellent introduction to the issues that are involved. It contains chapters that address the ways in which humans and machines attend to, recognize, and act toward objects in the visual environment.




Viewer-Centered Object Recognition in Monkeys


Book Description

How does the brain recognize three-dimensional objects? We trained monkeys to recognize computer rendered objects presented from an arbitrarily chosen {\it training} view, and subsequently tested their ability to generalize recognition for other views. Our results provide additional evidence in favor of with a recognition model that accomplishes view-invariant performance by storing a limited number of object views or templates together with the capacity to interpolate between the templates (Poggio and Edelman, 1990).




Visual Perception from a Computer Graphics Perspective


Book Description

This book provides an introduction to human visual perception suitable for readers studying or working in the fields of computer graphics and visualization, cognitive science, and visual neuroscience. It focuses on how computer graphics images are generated, rather than solely on the organization of the visual system itself; therefore, the text pro




Computer Vision and Computer Graphics - Theory and Applications


Book Description

INSTICC organized the third edition of VISIGRAPP that took place in Funchal- Madeira, Portugal in January 2008 after successful previous editions. This book - cludes selected papers from VISIGRAPP 2008, the Joint Conference on Computer Vision Theory and Applications (VISAPP) and Computer Graphics Theory and - plications (GRAPP). The conference was intended to stimulate the exchange of ideas on the topics of c- puter vision and computer graphics. We received a high number of paper submissions: 374 in total for both conferences. We had contributions from more than 50 countries in all continents. This confirms the success and global dimension of these jointly organized conferences. After a rigorous double-blind evaluation method, 78 submissions were accepted as full papers. From those, 20 were selected for this book. To ensure the sci- tific quality of the contributions, these were selected from the ones that were evaluated with the highest scores by the VISIGRAPP Program Committee Members and then they were extended and revised by the authors. Special thanks go to all contributors and re- rees, without whom this book would not have been possible. VISIGRAPP 2008 also featured the comments of keynote speakers, in alphabetical order, Adrian Hilton (University of Surrey, UK), Geneviève Lucet (Computer S- vices for Research at the UNAM, Mexico), Peter Sturm (INRIA Rhône-Alpes, France) and Sharathchandra Pankanti (IBM - Exploratory Computer Vision Group, USA), who are internationally recognized researchers. The presentations represented an - portant contribution to the overall quality of the conference.




Recognizing Variable Environments


Book Description

Normal adults do not have any difficulty in recognizing their homes. But can artificial systems do in the same way as humans? This book collects interdisciplinary evidences and presents an answer from the perspective of computing, namely, the theory of cognitive prism. To recognize an environment, an intelligent system only needs to classify objects, structures them based on the connection relation (not through measuring!), subjectively orders the objects, and compares with the target environment, whose knowledge is similarly structured. The intelligent system works, therefore, like a prism: when a beam of light (a scene) reaches (is perceived) to an optical prism (by an intelligent system), some light (objects) is reflected (are neglected), those passed through (the recognized objects) are distorted (are ordered differently). So comes the term 'cognitive prism'! Two fundamental propositions used in the theory can be informally stated as follow: an orientation relation is a kind of distance comparison relation -- you being in front of me means you being nearer to my face than to my other sides; a pair of objects being connected means any object, precisely the space occupied by the object, can be moved to a place where it connects with the pair.