X SIBGRAPI (1997) - Curso I2

Fuzzy Sets in Image Processing

Isabelle Bloch, Ecole Nationale Supérieure des Télécommunications - Département Images

Course description:
The aim of this course is to provide graduate students and researchers with an overview of the possible use of fuzzy sets in image processing, in particular for modeling, analysing and interpretating image information under imprecision. Research in this field becomes more and more active, and deserves to be known, both from a theoretical and from a practical point of view.
We will describe powerful features of fuzzy sets when used specifically for image . information processing. We have chosen to focus on three points:

the ability of fuzzy sets to represent spatial information in images along with its imprecision,
operations recently generalized to fuzzy sets in order to manage spatial information,
and information fusion using fuzzy combination operators.

We will illustrate these aspects by some examples of applications using fuzzy sets which show promising results from low level processing to higher level image interpretation. Indeed, applications of fuzzy logic and fuzzy sets to image processing are quite recent, compared with other fields like control, but they give rise now to a large development . This may be explained by several factors, and in particular by the ability of fuzzy sets to represent and to manage imprecise spatial information. Another factor is that this development can benefit of the degree of maturation of both image processing and fuzzy logic fields. On the other hand, the combination of these two fields did not yet gained a complete conviction and maturity as compared with other image processing techniques. However, fuzzy sets do have a high interest for image processing, which deserves a deeper attention.

[ contact author | slides | detailed description ]