The What-And-Where Filter: A Spatial Mapping Neural Network for Object Recognition and Image Understanding

The What-and-Where filter forms part of a neural network architecture for spatial mapping, object recognition, and image understanding. The Where fllter responds to an image figure that has been separated from its background. It generates a spatial map whose cell activations simultaneously represent the position, orientation, ancl size of all tbe figures in a scene (where they are). This spatial map may he used to direct spatially localized attention to these image features. A multiscale array of oriented detectors, followed by competitve and interpolative interactions between position, orientation, and size scales, is used to define the Where filter. This analysis discloses several issues that need to be dealt with by a spatial mapping system that is based upon oriented filters, such as the role of cliff filters with and without normalization, the double peak problem of maximum orientation across size scale, and the different self-similar interpolation properties across orientation than across size scale. Several computationally efficient Where filters are proposed. The Where filter rnay be used for parallel transformation of multiple image figures into invariant representations that are insensitive to the figures' original position, orientation, and size. These invariant figural representations form part of a system devoted to attentive object learning and recognition (what it is). Unlike some alternative models where serial search for a target occurs, a What and Where representation can he used to rapidly search in parallel for a desired target in a scene. Such a representation can also be used to learn multidimensional representations of objects and their spatial relationships for purposes of image understanding. The What-and-Where filter is inspired by neurobiological data showing that a Where processing stream in the cerebral cortex is used for attentive spatial localization and orientation, whereas a What processing stream is used for attentive object learning and recognition.

A Neural Network Architecture for Autonomous Learning, Recognition, and Prediction in a Nonstationary World

In a constantly changing world, humans are adapted to alternate routinely between attending to familiar objects and testing hypotheses about novel ones. We can rapidly learn to recognize and narne novel objects without unselectively disrupting our memories of familiar ones. We can notice fine details that differentiate nearly identical objects and generalize across broad classes of dissimilar objects. This chapter describes a class of self-organizing neural network architectures--called ARTMAP-- that are capable of fast, yet stable, on-line recognition learning, hypothesis testing, and naming in response to an arbitrary stream of input patterns (Carpenter, Grossberg, Markuzon, Reynolds, and Rosen, 1992; Carpenter, Grossberg, and Reynolds, 1991). The intrinsic stability of ARTMAP allows the system to learn incrementally for an unlimited period of time. System stability properties can be traced to the structure of its learned memories, which encode clusters of attended features into its recognition categories, rather than slow averages of category inputs. The level of detail in the learned attentional focus is determined moment-by-moment, depending on predictive success: an error due to over-generalization automatically focuses attention on additional input details enough of which are learned in a new recognition category so that the predictive error will not be repeated. An ARTMAP system creates an evolving map between a variable number of learned categories that compress one feature space (e.g., visual features) to learned categories of another feature space (e.g., auditory features). Input vectors can be either binary or analog. Computational properties of the networks enable them to perform significantly better in benchmark studies than alternative machine learning, genetic algorithm, or neural network models. Some of the critical problems that challenge and constrain any such autonomous learning system will next be illustrated. Design principles that work together to solve these problems are then outlined. These principles are realized in the ARTMAP architecture, which is specified as an algorithm. Finally, ARTMAP dynamics are illustrated by means of a series of benchmark simulations.

3-D Vision and Figure-Ground Separation by Visual Cortex

A neural network theory of :3-D vision, called FACADE Theory, is described. The theory proposes a solution of the classical figure-ground problem for biological vision. It does so by suggesting how boundary representations and surface representations are formed within a Boundary Contour System (BCS) and a Feature Contour System (FCS). The BCS and FCS interact reciprocally to form 3-D boundary and surface representations that arc mutually consistent. Their interactions generate 3-D percepts wherein occluding and occluded object completed, and grouped. The theory clarifies how preattentive processes of 3-D perception and figure-ground separation interact reciprocally with attentive processes of spatial localization, object recognition, and visual search. A new theory of stereopsis is proposed that predicts how cells sensitive to multiple spatial frequencies, disparities, and orientations are combined by context-sensitive filtering, competition, and cooperation to form coherent BCS boundary segmentations. Several factors contribute to figure-ground pop-out, including: boundary contrast between spatially contiguous boundaries, whether due to scenic differences in luminance, color, spatial frequency, or disparity; partially ordered interactions from larger spatial scales and disparities to smaller scales and disparities; and surface filling-in restricted to regions surrounded by a connected boundary. Phenomena such as 3-D pop-out from a 2-D picture, DaVinci stereopsis, a 3-D neon color spreading, completion of partially occluded objects, and figure-ground reversals are analysed. The BCS and FCS sub-systems model aspects of how the two parvocellular cortical processing streams that join the Lateral Geniculate Nucleus to prestriate cortical area V4 interact to generate a multiplexed representation of Form-And-Color-And-Depth, or FACADE, within area V4. Area V4 is suggested to support figure-ground separation and to interact. with cortical mechanisms of spatial attention, attentive objcect learning, and visual search. Adaptive Resonance Theory (ART) mechanisms model aspects of how prestriate visual cortex interacts reciprocally with a visual object recognition system in inferotemporal cortex (IT) for purposes of attentive object learning and categorization. Object attention mechanisms of the What cortical processing stream through IT cortex are distinguished from spatial attention mechanisms of the Where cortical processing stream through parietal cortex. Parvocellular BCS and FCS signals interact with the model What stream. Parvocellular FCS and magnocellular Motion BCS signals interact with the model Where stream. Reciprocal interactions between these visual, What, and Where mechanisms arc used to discuss data about visual search and saccadic eye movements, including fast search of conjunctive targets, search of 3-D surfaces, selective search of like-colored targets, attentive tracking of multi-element groupings, and recursive search of simultaneously presented targets.

Restoration of optical objects using regularization

Using the regularization theory for improperly posed problems, we discuss object restoration beyond the diffraction limit in the presence of noise. Only the case of one-dimensional coherent objects is considered. We focus attention n the estimation of the error on the restored objects, and we show that, in most realistic cases, it is at best proportional to an inverse power of

Computer Museum, School of Computing and Mathematical Sciences, University of Greenwich

Computer equipment, once viewed as leading edge, is quickly condemned as obsolete and banished to basement store rooms or rubbish bins. The magpie instincts of some of the academics and technicians at the University of Greenwich, London, preserved some such relics in cluttered offices and garages to the dismay of colleagues and partners. When the University moved into its new campus in the historic buildings of the Old Royal Naval College in the center of Greenwich, corridor space in King William Court provided an opportunity to display some of this equipment so that students could see these objects and gain a more vivid appreciation of their subject's history.

Fact, fiction and nostalgia: an assessment of heritage interpretation at living museums

This paper aims to explore and discuss the role of nostalgia (a concept that is inherently grounded within a psychological framework) in heritage interpretation from both provider and consumer perspectives. Whilst many cultural practitioners recognise the relationship between sentimentality and authenticity, particularly within a folk-heritage context, few have sought to examine the effect this has on the visitor experience. This paper questions visitors’ ability to objectively assess objects and experiences at heritage sites, and the role of practitioners in presenting often blurred views of social history that may sometimes negate historical fact. Drawing on case study research at two UK living museums, Blists Hill Victorian Town in Shropshire, England, and the Big Pit: National Coal Museum in Wales, notions of reminiscence, authenticity, myth and intangibility are considered within the framework of the interpretive experience. Findings suggest that the visitor experience is inherently subjective, highly individual and that the concept of intangibility is integral to an understanding of the nostalgia-authenticity debate.

Art, adolescence and Social Work: Anja, the invisible manager

This article has been written with the intention of being able to analyse the contributions of art —theatre, in this case— to the practice of social work. For this purpose, we have chosen to read the social reality in which we intervene through the lens of social constructionism. This helps us to rescue the social and subjective side of art, and, moreover, to recover the depathologization of the subject in professional intervention. Thus, using a practical case taken from work with adolescents in the German FSJ programme, hand-in-hand with a young girl called Anja we trace the developmental and sociological aspects of adolescence in order to later address certain common points of art and psychosocial work. Art will hence be redefined as a transitional object allowing questions to be addressed relating to (self-) perception, attachment, communication and changes in conduct as the ultimate goal of professional action. Lastly, we note the limitations and risks of art-based intervention, in order to conclude with a final synopsis.

'National Antiquities' and the Law

National museums, housing â??national antiquities', were a nineteenth-century cultural phenomenon throughout Europe. In the United Kingdom, they afforded the Treasury a means of preserving relics of antiquity claimed as treasure trove. While satisfying the desire of the scientific community for the preservation of archaeological finds, and national sentiment in Scotland and Ireland, Treasury practice undermined the British Museum's eponymous mission. This paper traces the development and legal consequences of the Treasury policy of national allocation of treasure trove, including the discussion in the Museums Committee of 1898â??99 of the â??nationality' of objects and artefacts, and considers the potential wider significance of â??national antiquity' in the context of changing constitutional arrangements in the United Kingdom in the 1920s, and in the future.

Investigating shape-from-shading illusions using solid objects

Recent growth in the shape-from-shading psychophysics literature has been paralled by an increasing availability of computer graphics hardware and software, to the extent that most psychophysical studies in this area now employ computer lighting algorithms. The most widely used of algorithms is shape-from-shading psychophysics is the Phong lighting model. This model, and other shading models of its genre, produce readily ineterpretable imiages of three-dimensional scenes. However, such algorithms are only approximations of how light interacts with real objects in the natural environment. Nevertheless, the results from psychophysical experiments using these techniques have been used to infer the processes underlying the perception of shape-from-shading in natural environments. It is important to establish whether this substitution is ever valid. We report a series of experiments investigating whether two recently reported illusions seen computer-generated, Phond shaded images occur for solid objects under real illuminants. The two illusions investigated are three-dimensional curvature contrast and the illuminant-position effect on perceived curvature. We show that both effects do occur for solid objects, and that the magnitude of these effects are equivalent regardless of whether subjects are presented with ray traced or solid objects.

Selection Power and Selection Labor for Information Retrieval

This study examines the relation between selection power and selection labor for information retrieval (IR). It is the first part of the development of a labor theoretic approach to IR. Existing models for evaluation of IR systems are reviewed and the distinction of operational from experimental systems partly dissolved. The often covert, but powerful, influence from technology on practice and theory is rendered explicit. Selection power is understood as the human ability to make informed choices between objects or representations of objects and is adopted as the primary value for IR. Selection power is conceived as a property of human consciousness, which can be assisted or frustrated by system design. The concept of selection power is further elucidated, and its value supported, by an example of the discrimination enabled by index descriptions, the discovery of analogous concepts in partly independent scholarly and wider public discourses, and its embodiment in the design and use of systems. Selection power is regarded as produced by selection labor, with the nature of that labor changing with different historical conditions and concurrent information technologies. Selection labor can itself be decomposed into description and search labor. Selection labor and its decomposition into description and search labor will be treated in a subsequent article, in a further development of a labor theoretic approach to information retrieval.

Correlating Additives to Deterioration and Assessing the Effectiveness of Acrylic Coatings for the Protection of Rubber

Conservators have long been aware of the problems associated with the preservation of rubber objects due to inherent instability that can be attributed, in part, to the presence of additives. Inorganic additives, such as fillers, accelerators, stabilizers, and special ingredients are necessary in manufacturing to alter the properties of natural rubber. These materials all have different interactions with the rubber, and each other, and differing effects on the ageing process. To date, the most effective and accepted methods to preserve rubber are cold, dark storage of objects, or the use of low oxygen environments. While these methods are effective, they greatly limit access. The application of coatings to the surface of rubber objects can slow deterioration and greatly increase the ability of an institution to handle and display rubber objects. While numerous coatings for preventive and interventive treatment have been tested, none have been so successful to warrant routine use. The first section of this research highlighted the relationship between the inclusion of certain additives in natural rubber objects and the accelerated or slowed down overall degradation. In the second part of this research, the acrylic varnishes Golden Polymer Varnish with UVLS, Lascaux Acrylic Transparent Varnish-UV, Sennelier Matte Lacquer with UV Protection, and Liquitex Soluvar Varnish containing ultraviolet light absorbers or stabilizers were tested as a preventative coating for rubber. Through testing the visual and physical properties of the samples, as well as compound analysis the results of this research suggest that acrylic varnishes do provide protection, each to varying degrees. The results also provided insight into the behavior of rubber and these varnishes with continuing light exposure.

Field configured assembly: Programmed manipulation and self-assembly at the mesoscale

Field configured assembly is a programmable force field method that permits rapid, "hands-free" manipulation, assembly, and integration of mesoscale objects and devices. In this method, electric fields, configured by specific addressing of receptor and counter electrode sites pre-patterned at a silicon chip substrate, drive the field assisted transport, positioning, and localization of mesoscale devices at selected receptor locations. Using this approach, we demonstrate field configured deterministic and stochastic self-assembly of model mesoscale devices, i.e., 50 mum diameter, 670 nm emitting GaAs-based light emitting diodes, at targeted receptor sites on a silicon chip. The versatility of the field configured assembly method suggests that it is applicable to self-assembly of a wide variety of functionally integrated nanoscale and mesoscale systems.

The VLT-FLAMES survey of massive stars: evolution of surface N abundances and effective temperature scales in the Galaxy and Magellanic Clouds

We present an analysis of high resolution VLT-FLAMES spectra of 61 B-type stars with relatively narrow-lined spectra located in 4 fields centered on the Milky Way clusters; NGC 3293 and NGC 4755 and the Large and Small Magellanic cloud clusters; NGC 2004 and NGC 330. For each object a quantitative analysis was carried out using the non-LTE model atmosphere code TLUSTY; resulting in the determination of their atmospheric parameters and photospheric abundances of the dominant metal species (C, N, O, Mg, Si, Fe). The results are discussed in relation to our earlier work on 3 younger clusters in these galaxies; NGC 6611, N11 and NGC 346 paying particular attention to the nitrogen abundances which are an important probe of the role of rotation in the evolution of stars. This work along with that of the younger clusters provides a consistent dataset of abundances and atmospheric parameters for over 100 B-type stars in the three galaxies. We provide effective temperature scales for B-type dwarfs in all three galaxies and for giants and supergiants in the SMC and LMC. In each galaxy a dependence on luminosity is found between the three classes with the unevolved dwarf objects having significantly higher effective temperatures. A metallicity dependence is present between the SMC and Galactic dwarf objects, and whilst the LMC stars are only slightly cooler than the SMC stars, they are significantly hotter than their Galactic counterparts.

The atmospheric parameters and chemical composition of early B-type giants in h and chi Persei

Atmospheric parameters and surface chemical compositions are presented for eight stars, classified as B1 or B2 but with a range of luminosity classes, in the northern double cluster h and chi Persei. Echelle spectroscopy (covering the wavelength region 3900 to 4700 Ä) and grating spectroscopy (of the Balmer, H? and Hß lines) were analysed using non-LTE synthetic spectra based on LTE line-blanketed atmosphere structures. High microturbulences are found in our sample, and this quantity must be included in the computation of the non-LTE level populations; its effect is generally to decrease the derived metal abundances by typically 0.1 dex but by up to 0.4 dex. Our absolute abundances are in reasonable agreement with those previously found for main sequence B-type stars, while we find some evidence for small abundance variations (particularly for nitrogen) within our sample. One star (BD+56 678) appears to be a spectrum variable and at two epochs shows a highly enriched nitrogen spectrum. Our atmospheric parameters imply that two stars have previously been mis-identified as main sequence objects and a distance modulus, at the higher end of the values previously deduced. The observational HR diagram is consistent with stellar evolutionary models that explicitly include the effects of rotation.

Reducing the mapping between perception and action facilitates imitation

This study investigated two hypotheses regarding the mapping of perception to action during imitation. The first hypothesis predicted that as children’s cognitive capacities increase the tendency to map one goal and disregard others during imitation should decrease. This hypothesis was tested by comparing the performances of 168 4- to 7-year-olds in a gestural imitation task developed by Bekkering, Wohlschläger, and Gattis. The second hypothesis predicted that reducing the mapping between perception and action should reduce the demands on the cognitive resources of the child. This hypothesis was tested by creating a condition in which perception and action overlapped by sharing objects between experimenter and child. In three experimental conditions, an adult modelled four gestures, directed at either: 1) one of two sets of round stickers (proprietary objects); 2) the same location on the table, without any sticker (no objects); or 3) one set of round stickers, which were shared with the child (shared objects). The results confirmed both hypotheses. Four- and five-year-olds imitated less accurately when imitation involved mapping of both objects and movements (proprietary and shared objects) than when imitation involved mapping movements only (no objects). Seven-year-olds imitated accurately in all three conditions, demonstrating that increased cognitive capacity allowed them to map multiple goals from perception to action. Most importantly, reducing the mapping between perception and action in the shared objects condition facilitated imitation, specifically for the transitional group, 6-year-olds. We conclude that mapping between perception and action is not direct, but resembles mapping relations in analogical reasoning: cognitive processes mediate mapping from perception to action.