You are here


Primary tabs

  1. Ornella Mich,
    Viewpoint Dependence in Face Recognition,
    This paper analyzes the problem of face recognition as a cognitive process. Specifically, it studies the influence of the angle from which the face to recognize is observed. Following the examination of studies that considered this problem in the past, two psychophysical experiments are presented that seek to further clarify the problem. It is shown that the subject gives different responses according to target viewpoint, with the surest and most rapid recognition coming from observation of the right-hand side of the face.,
  2. F. Panaget,
    The Micro-Planning Component of a Generation System,
  3. G. Criscuolo; Fausto Giunchiglia; Luciano Serafini,
    A Foundation of Metalogical Reasoning: OM Pairs (Propositional Case),
    In this paper we propose a framework, called OM pairs, for the formalization of reasoning with meta theories. OM pairs allow us to generate deductively the object theory and/or the meta theory by imposing via appropriate reflection rules, the relation we want to hold between the object and meta theory themselves. We study OM pairs from three different points of view: we compare the stength of the object and meta theories generated by different OM pairs. For each OM pair we study the precise form of the object theory and meta theory. For each OM pair we study the relation between the models of the meta theory and the object theory,
  4. Bianca Angelini; Fabio Brugnara; D. Falavigna; Diego Giuliani; Roberto Gretter; Maurizio Omologo,
    Speaker Independent Continuous Speech Recognition using an Acoustic-Phonetic Italian Corpus,
  5. Diego Giuliani; Maurizio Omologo; Piergiorgio Svaizer,
    Talker Localization and Speech Recognition Using a Microphone Array and a Cross-PowerSpectrum Phase Analysis,
  6. A. Artale; E. Franconi,
    Time, Actions and Plans Representation in a Description Logic,
    A formal language for representing and reasoning about time, actions and plans in a uniform way is presented. We employ an action representation in the style of Allen, where an action is represented by describing what is true while the action is occurring. In this sense, an action is defined by means of temporal constraints on the world states, which pertain to the action itself, and on other more elementary actions occurring over time. A distinction between action types and individual actions is supported by the formalism. Plans are seen as complex actions whose properties possibly change with time. Therefore, the distinction between actions and plans disappears in this framework. The formal representation language used in this paper is a member of the family of description logics, and it is provided with a well founded syntax, semantics and calculus. The classification and recognition tasks, together with the basic subsumption procedure, form the basis for action management. An action description can be automatically classified into a taxonomy; an action instance can be recognized to take place at a certain moment from the observation of what is happening in the world during a time interval,
  7. Giovanni Soncini; Amos Collini; Mario Zen; Nicola Zorzi,
    Progetto bioelettronica VLSI specifiche relative ai fotosensori elementari CCD,
  8. Amos Collini; Nicola Zorzi,
    Project MInOSS: Results of Spectral Response Measurements on the Photodiodes,
    A study of the electro-optical characteristics of CMOS-compatible photodiodes has been performed in the frame of the MInOSS project. This work reports the responsivity measurements carried out on twelve technologically different photosensors. After a brief description of the experimental set-up and of the measurements procedure, the spectral response results are presented, compared and discussed. Finally, a summary of the main conclusions is reported.,
  9. B. Crespi; Dimitri Giordani; L. Stringa,
    Memory-based sensor integration,
    A sonar array and a camera are the sensors of a robot that learns to move inside a building. Learning is based on the association of ultrasonic and visual images with motor commands. The two sensors extract different information from the environment. Sonars produce a short-range depth image on the sonar array plane, vision gives a wide-range flat image of the space. In this work, a memory-based probabilistic framework is developed that integrates the information gathered by the sensors,
  10. I.R.S.T.,
    Studio di fattibilità di una macchina automatica per il taglio di cubetti di porfido,