Attraction based recognition

Author

Tascini, Guido ; Zingaretti, Primo

Author_Institution

Istituto di Inf., Ancona Univ., Italy

Volume

3

fYear

1994

fDate

2-5 Oct 1994

Firstpage

2378

Abstract

We introduce, in a model driven recognition approach, the principle of attraction which influences all transformations that may be done, departing from the first image, in order to reach the recognition of objects in a scene. The representation of knowledge has to be reduced to a representation in the feature space. This paper attempts to consider the behaviour of image transformation, for recognition purpose, in this vector space. After the definition of the attraction principle, we describe the attraction process, justify the image chaining concept, and finally interpret a series of processes, including the segmentation refinement, search space reduction and perceptual organization, in terms of the attraction principle

Keywords

computer vision; feature extraction; image segmentation; knowledge based systems; object recognition; search problems; attraction based object recognition; computer vision; feature space; image chaining; image segmentation; image transformation; knowledge based system; model driven image recognition; perceptual organization; search space reduction; vector space; Computer vision; Degradation; Image recognition; Informatics; Layout; Object recognition; Predictive models; Robustness; Shape; Solid modeling;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1994. Humans, Information and Technology., 1994 IEEE International Conference on

Conference_Location

San Antonio, TX

Print_ISBN

0-7803-2129-4

Type

conf

DOI

10.1109/ICSMC.1994.400222

Filename

400222