Straipsnyje nagrinėjami T. Valentine’o veidų erdvės ir M. B. Lewiso bei R. A. Johnstono Voronoi modeliai, kuriuose pagrindinis dėmesys skiriamas veidų reprezentacijos atmintyje ypatumams. Pažymima, jog veidai reprezentuojami hipotetinėje daugiamatėje veidų erdvėje. Veidų erdvės matmenys (arba geometrinės ašys) atspindi koduojamos veido informacijos požymių įverčius. Tuomet pats veidas apibūdinamas kaip unikalus įvairių matmenų įverčių derinys, kuris gali būti reprezentuotas veidų erdvėje kaip vienintelis abstraktus taškas arba vektorius (pagal tai, ar kodavimo metu atsižvelgiama į veidą-prototipą). Remiantis veidų išsidėstymo erdvėje principais (nuotoliu nuo veido-prototipo ir atstumu tarp reprezentuojamų veidų) aiškinami kai kurie veidų informacijos apdorojimo dėsningumai (pvz., informacijos atgaminimo tikslumas, veidų tarpusavio panašumo, savitumo / tipiškumo nustatymas ir pan.). Pagrindinė problema – netikslus ir nedetalus modeliuose vartojamų sąvokų bei aprašomų veido informacijos apdorojimo procesų apibūdinimas. Tai lemia atliekamų tyrimų rezultatų prieštaringumą ir pasunkina empirinį modelių prielaidų patvirtinimą.
MODELS OF FACES REPRESENTATIONKristina Vanagaitė
SummaryConsidering that information alteration of faces and other visual stimulus differ qualitative, it is important to establish models, which would enable to explain peculiar consistent patterns of information processing of faces.One of the most important stages of informatikon processing – representation in memory. Recently, seeking to discover the peculiarities of faces representation in memory, the biggest attention is given to face space of T. Valentine and patterns of M. B. Lewis and R. A. Johnston Voronoi.In T. Valentine’s multidimensional face-space framework, faces are encoded according to a series of visual or physical parameter particular to each face. Each of these parameters is represented along a space dimension. The dimensions of the space will be those that serve to discriminate between faces and they represent the perceptual dimensions or features of faces that distinguish the faces. A face’s representation will be made up of many values taken along many different dimensions. This set of values will be unique for every individual face and will be represented as a single point (or vector) in an N-dimensional face-space. The main problem – because of non-comprehensive description of face’s dimension and encoded information of faces it is not clear the way of distinguishing physical and psychological faces’ dimensions, the possibilities to range the encoded face dimensions according to their importance and significance.Two different models based on this framework, norm-based and exemplar-based models are described and contrasted. Models that incorporate the facial prototype are referred to as norm-based models. On such models, faces are represented by face vectors taken relative to the facial prototype at the center of the face-space, which represent the average value of the population on each dimension. Although the existence of face-prototype is certified by the research of faces’ caricature, it is unclear why the faces of representatives of other races are reproduced inaccurate, how are the valuation mediums of encoded faces’ dimension calculated, does the face-prototype is kept in memory as the real face?As an alternative to these – exemplar-based models have face representations that are stored as absolutes, relative only to other exemplars. The present study describes Voronoi diagram, developed from the exemplar-based model, which accounts for the caricature advantage without reference to an explicitly encoded facial prototype. Voronoi diagram involves interpreting the face-space as a space of regions of identity (also called „Voronoi cells“) rather than a set of points or vectors. The advantage of this pattern – the identity of observed face is connected with appropriate „cell“. It is important, because such structure, differently to the pattern oriented to standard, enables to explain the fact, that faces are recognized despite their dimensions or change of circumstances of observation.Distinguishing between these two models remains difficult because they make similar predictions. For example, both models predict that faces that are judged to be distinctive will be recognized faster and more accurately than those judged to be typical. Also indicate that typical faces are generally located near the center of the space in more densely populated facespace while distinctive faces will tend to be present in the outer regions. However, with help of patterns oriented to standards, as well as to examples, it is possible to explain only some of peculiarities of informatikon alteration of faces and the results of empirical researches are quite contradictory. Further analysis of pattern of faces’ expansion is necessary – it would not only specify the hypothetical structure of faces’ expansion, but also elaborate the proceeding processes.
A NEW UNCONSCIOUS PARADIGM AT THE HEART OF MATHEMATICS AND PHYSICS
