Vision


Book Description

Available again, an influential book that offers a framework for understanding visual perception and considers fundamental questions about the brain and its functions. David Marr's posthumously published Vision (1982) influenced a generation of brain and cognitive scientists, inspiring many to enter the field. In Vision, Marr describes a general framework for understanding visual perception and touches on broader questions about how the brain and its functions can be studied and understood. Researchers from a range of brain and cognitive sciences have long valued Marr's creativity, intellectual power, and ability to integrate insights and data from neuroscience, psychology, and computation. This MIT Press edition makes Marr's influential work available to a new generation of students and scientists. In Marr's framework, the process of vision constructs a set of representations, starting from a description of the input image and culminating with a description of three-dimensional objects in the surrounding environment. A central theme, and one that has had far-reaching influence in both neuroscience and cognitive science, is the notion of different levels of analysis—in Marr's framework, the computational level, the algorithmic level, and the hardware implementation level. Now, thirty years later, the main problems that occupied Marr remain fundamental open problems in the study of perception. Vision provides inspiration for the continuing efforts to integrate knowledge from cognition and computation to understand vision and the brain.




Representation and Recognition in Vision


Book Description

Shimon Edelman bases a comprehensive approach to visual representation on the notion of correspondence between proximal (internal) and distal similarities in objects. Researchers have long sought to understand what the brain does when we see an object, what two people have in common when they see the same object, and what a "seeing" machine would need to have in common with a human visual system. Recent neurobiological and computational advances in the study of vision have now brought us close to answering these and other questions about representation. In Representation and Recognition in Vision, Shimon Edelman bases a comprehensive approach to visual representation on the notion of correspondence between proximal (internal) and distal similarities in objects. This leads to a computationally feasible and formally veridical representation of distal objects that addresses the needs of shape categorization and can be used to derive models of perceived similarity. Edelman first discusses the representational needs of various visual recognition tasks, and surveys current theories of representation in this context. He then develops a theory of representation that is related to Shepard's notion of second-order isomorphism between representations and their targets. Edelman goes beyond Shepard by specifying the conditions under which the representations can be made formally veridical. Edelman assesses his theory's performance in identification and categorization of 3D shapes and examines it in light of psychological and neurobiological data concerning the object-processing stream in primate vision. He also discusses the connections between his theory and other efforts to understand representation in the brain.




Vision and Mind


Book Description

The philosophy of perception is a microcosm of the metaphysics of mind. Its central problems—What is perception? What is the nature of perceptual consciousness? How can one fit an account of perceptual experience into a broader account of the nature of the mind and the world?—are at the heart of metaphysics. Rather than try to cover all of the many strands in the philosophy of perception, this book focuses on a particular orthodoxy about the nature of visual perception. The central problem for visual science has been to explain how the brain bridges the gap between what is given to the visual system and what is actually experienced by the perceiver. The orthodox view of perception is that it is a process whereby the brain, or a dedicated subsystem of the brain, builds up representations of relevant figures of the environment on the basis of information encoded by the sensory receptors. Most adherents of the orthodox view also believe that for every conscious perceptual state of the subject, there is a particular set of neurons whose activities are sufficient for the occurrence of that state. Some of the essays in this book defend the orthodoxy; most criticize it; and some propose alternatives to it. Many of the essays are classics. Contributors G.E.M. Anscombe, Dana Ballard, Daniel Dennett, Fred Dretske, Jerry Fodor, H.P. Grice, David Marr, Maurice Merleau-Ponty, Zenon Pylyshyn, Paul Snowdon, and P.F. Strawson




Hierarchical Object Representations in the Visual Cortex and Computer Vision


Book Description

Over the past 40 years, neurobiology and computational neuroscience has proved that deeper understanding of visual processes in humans and non-human primates can lead to important advancements in computational perception theories and systems. One of the main difficulties that arises when designing automatic vision systems is developing a mechanism that can recognize - or simply find - an object when faced with all the possible variations that may occur in a natural scene, with the ease of the primate visual system. The area of the brain in primates that is dedicated at analyzing visual information is the visual cortex. The visual cortex performs a wide variety of complex tasks by means of simple operations. These seemingly simple operations are applied to several layers of neurons organized into a hierarchy, the layers representing increasingly complex, abstract intermediate processing stages. In this Research Topic we propose to bring together current efforts in neurophysiology and computer vision in order 1) To understand how the visual cortex encodes an object from a starting point where neurons respond to lines, bars or edges to the representation of an object at the top of the hierarchy that is invariant to illumination, size, location, viewpoint, rotation and robust to occlusions and clutter; and 2) How the design of automatic vision systems benefit from that knowledge to get closer to human accuracy, efficiency and robustness to variations.




Sparse Representations and Compressive Sensing for Imaging and Vision


Book Description

Compressed sensing or compressive sensing is a new concept in signal processing where one measures a small number of non-adaptive linear combinations of the signal. These measurements are usually much smaller than the number of samples that define the signal. From these small numbers of measurements, the signal is then reconstructed by non-linear procedure. Compressed sensing has recently emerged as a powerful tool for efficiently processing data in non-traditional ways. In this book, we highlight some of the key mathematical insights underlying sparse representation and compressed sensing and illustrate the role of these theories in classical vision, imaging and biometrics problems.




Vision, Devotion, and Self-Representation in Late Medieval Art


Book Description

Focuses on one of the most attractive features of late medieval manuscript illumination: the portrait of the book owner at prayer within the pages of her prayer-book.




Touch and Blindness


Book Description

Research on touch and blindness has undergone rapid transformation in recent years, with dramatic developments in technology designed to provide assistance to those who are blind, and advancements in robotics that demand haptic interfaces. Touch and Blindness approaches the study of the topic from the perspectives of psychological methodology and the most sophisticated, state-of-the-art techniques in neuroscience. This book, edited by well-known leaders in the field, is derived from the discussions presented by speakers at a conference held in 2002, and presents current research in the field. The book is arranged in a logical, disciplinary fashion, first discussing touch and blindness from a psychological perspective, followed by an examination from the perspective of neuroscience. Some specific topics include: *processing spatial information from touch and movement; *form, projection, and pictures for the blind; *neural substrate and visual and tactile object representations; and *the role of visual cortex in tactile processing. Touch and Blindness is ideal for researchers in psychology and neuroscience, medicine, and special education.




Foundations of Vision


Book Description

Designed for students, scientists and engineers interested in learning about the core ideas of vision science, this volume brings together the broad range of data and theory accumulated in this field.




Medial Representations


Book Description

The last half century has seen the development of many biological or physical t- ories that have explicitly or implicitly involved medial descriptions of objects and other spatial entities in our world. Simultaneously mathematicians have studied the properties of these skeletal descriptions of shape, and, stimulated by the many areas where medial models are useful, computer scientists and engineers have developed numerous algorithms for computing and using these models. We bring this kno- edge and experience together into this book in order to make medial technology more widely understood and used. The book consists of an introductory chapter, two chapters on the major mat- matical results on medial representations, ?ve chapters on algorithms for extracting medial models from boundary or binary image descriptions of objects, and three chapters on applications in image analysis and other areas of study and design. We hope that this book will serve the science and engineering communities using medial models and will provide learning material for students entering this ?eld. We are fortunate to have recruited many of the world leaders in medial theory, algorithms, and applications to write chapters in this book. We thank them for their signi?cant effort in preparing their contributions. We have edited these chapters and have combined them with the ?ve chapters that we have written to produce an integrated whole.




Aesthetic Computing


Book Description

The application of the theory and practice of art to computer science: how aesthetics and art can play a role in computing disciplines.