DocumentCode :
3487768
Title :
On the use of size functions for shape analysis
Author :
Verri, Alessandro ; Uras, C. ; Frosini, P. ; Ferri, M.
Author_Institution :
Dipartimento di Fisica, Genova Univ., Italy
fYear :
1993
fDate :
34134
Firstpage :
89
Lastpage :
96
Abstract :
According to a recent mathematical theory a shape can be represented by functions, named size functions, which convey information on both the topological and metric properties of the viewed shape. The relevance of the theory of size functions to computer vision is investigated. An algorithm for the computation of the size functions is presented and many theoretical properties of the theory are demonstrated on real images. It is shown that the representation of shape in terms of size functions (i) can be tailored to suit the invariance of the problem at hand and (ii) is stable against small qualitative and quantitative changes of the viewed shape. A distance between size functions is used as a similarity measure between the representation of two different shapes. The obtained results indicate that size functions are likely to be very useful for object recognition. In particular, they seem to be well suited for the recognition of natural and articulated objects
Keywords :
computer vision; image recognition; computer vision; mathematical theory; metric properties; object recognition; shape analysis; size functions; viewed shape; Character recognition; Humans; Image recognition; Independent component analysis; Information analysis; Manufacturing; Object recognition; Shape measurement; Size measurement; Visual system;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Qualitative Vision, 1993., Proceedings of IEEE Workshop on
Conference_Location :
New York City, NY
Print_ISBN :
0-8186-3692-0
Type :
conf
DOI :
10.1109/WQV.1993.262946
Filename :
262946
Link To Document :
بازگشت