Record Display for the EPA National Library Catalog

RECORD NUMBER: 87 OF 103

Main Title The Making of a Neuromorphic Visual System [electronic resource] /
Type EBOOK
Author Rasche, Christoph.
Publisher Springer US,
Year Published 2005
Call Number RC321-580
ISBN 9780387234694
Subjects Medicine ; Neurosciences ; Neurobiology ; Microwaves ; Biomedical engineering
Internet Access
Description Access URL
http://dx.doi.org/10.1007/b101575
Collation XI, 140 p. online resource.
Notes
Due to license restrictions, this resource is available to EPA employees and authorized contractors only
Contents Notes
Seeing: Blazing Processing Characteristics -- Category Representation and Recognition Evolvement -- Neuroscientific Inspiration -- Neuromorphic Tools -- Insight From Line Drawings Studies -- Retina Circuits Signaling and Propagating Contours -- The Symmetric-Axis Transform -- Motion Detection -- Neuromorphic Architectures: Pieces and Proposals -- Shape Recognition with Contour Propagation Fields -- Scene Recognition -- Summary. The reader is presented an approach to the construction of a visual system, which is behaviorally, computationally and neurally motivated. The central goal is to characterize the process of visual categorization and to find a suitable representation format that can successfully deal with the structural variability existent within visual categories. It does not define such representations a priori but attempts to show directions on how to gradually work towards them. The book reviews past and existent theories of visual object and shape recognition in the fields of computer vision, neuroscience and psychology. The entire range of computations is discussed, as for example contour extraction in retinal circuits, orientation determination in cortical networks, position and scale independence of shape, as well as the issue of object and shape representation in a neural substrate. Region-based approaches are discussed and are modeled with wave-propagating networks. It is demonstrated how those networks operate on gray-scale images. A completely novel shape recognition architecture is proposed that can recognize simple shapes under various degraded conditions. It is discussed how such networks can be used for constructing basic-level object representations. It is envisioned how those networks can be implemented using the method of neuromorphic engineering, an analog electronic hardware substrate than can run neural computations in real-time and with little power.