Innovative modelling techniques in computer vision

Abstract The paper is concerned with two of main research activities currently carried on at the Computer Science and Artificial Intelligence lab of DIE. The first part deals with hybrid artificial vision models, intended to provide object recognition and classification capabilities to an autonomous intelligen system. In this framework, a system recovering 3-D shape information from grey-level images of a scene, building a geometric representation of the scene in terms of superquadrics at the geometric level, and reasoning about the scene at the symbolic level is described. In the second part, attention is focused on automatic indexing of image databases. JACOB, a prototypal system allowing for the automatic extraction from images of salient features like colour and texture, and for content-based browsing and querying in image and video databases is briefly described.

[1]  Bernhard Nebel,et al.  Reasoning and Revision in Hybrid Representation Systems , 1990, Lecture Notes in Computer Science.

[2]  Salvatore Gaglio,et al.  A Cognitive Architecture for Artificial Vision , 1997, Artif. Intell..

[3]  Dragutin Petkovic,et al.  Query by Image and Video Content: The QBIC System , 1995, Computer.

[4]  Edoardo Ardizzone,et al.  JACOB: just a content-based query system for video databases , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[5]  P. Gärdenfors.  Three levels of inductive inference , 1995 .

[6]  Barr,et al.  Superquadrics and Angle-Preserving Transformations , 1981, IEEE Computer Graphics and Applications.

[7]  Alex Pentland,et al.  Perceptual Organization and the Representation of Natural Form , 1986, Artif. Intell..

[8]  Ronald C. Arkin,et al.  Intelligent Robotic Systems , 1995, IEEE Expert.

[9]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[10]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[11]  Edoardo Ardizzone,et al.  Geometric and conceptual knowledge representation within a generative model of visual perception , 1989, J. Intell. Robotic Syst..