Fuzzy classification systems

Amo, Ana del; Montero, Javier; Biging, Gregory S.; Cutello, Vincenzo

doi:10.1016/s0377-2217(03)00002-x

Cited by 102 publications

(73 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…2,4 . The coloring procedure we present here is defined by means of a divisive crisp binary coloring process, which seems promising as a helpful tool in order to find out consistent regions and postulate possible fuzzy classes.…”

Section: Introductionmentioning

confidence: 99%

A Coloring Algorithm for Image Classification

Gómez

Montero²,

Poidomani³

2004

Applied Computational Intelligence

Self Cite

View full text Add to dashboard Cite

In this paper we present a pixel coloring algorithm, to be considered as a tool in fuzzy classification. Such an algorithm is based upon a sequential application of a divisive binary procedure on a fuzzy graph associated to the image to be classified, taking into account surrounding pixels. Each color will suggest a possible class, if homogeneous, and the hierarchical structure of colors will allow gradation between classes.

show abstract

Section: Introductionmentioning

confidence: 99%

A Coloring Algorithm for Image Classification

Gómez

Montero²,

Poidomani³

2004

Applied Computational Intelligence

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our point is that neutral predicates will naturally emerge from opposites: as in classification context (see, e.g., [1], [2]), two opposite predicates (e.g., tall/short) that refer to the same notion (height) and, depending on their semantics, can generate different neutral concepts. When opposites overlap (e.g., more or less tall/more or less short), both opposites are perhaps too wide and ambivalence appears as neutral predicate (to some extent both opposite predicates hold).…”

Section: Paired Fuzzy Sets and Paired Fuzzy Structuresmentioning

confidence: 99%

“…but assume expressions (2) and (3) to hold regarding the logical relationships between a property and its negation in terms of logical truth and falsehood. Thus, bipolar models enable to model opposite arguments at the level of knowledge representation, assuming two separate coordinates or dimensions (usually referred to as positive evidence and negative evidence, respectively) of knowledge representation, each of these dimensions in turn assuming a classical logic framework.…”

Section: Bipolar Knowledge Representation Modelsmentioning

confidence: 99%

Paired Structures and other opposites-based models

Rodríguez

Franco

Gómez

et al. 2015

Proceedings of the 2015 Conference of the International Fuzzy Systems Association and the European Society for Fuzzy Logic and

View full text Add to dashboard Cite

In this paper we present a new class of fuzzy sets, paired fuzzy sets, that tries to overcome any conflict between families of fuzzy sets that share a main characteristic: that they are generated from two basic opposite fuzzy sets. Hence, the first issue is to formalize the notion of opposition, that we will assume dependent on a specific negation, previously determined. In this way we can define a paired fuzzy set as a couple of opposite valuation fuzzy sets. Then we shall explore what kind of new valuation fuzzy sets can be generated from the semantic tension between those two poles, leading to a more complex valuation structure that still keeps the essence of being paired. In this way several neutral fuzzy sets can appear, in particular indeterminacy, ambivalence and conflict. Two consequences are then presented: on one hand, we will show how Atanassov´s Intuitionistic Fuzzy Sets can be viewed as a particular paired structure when the classical fuzzy negation is considered; on the other hand, the relationship of this model with bipolarity is reconsidered from our paired view.

show abstract

“…As a first step we modeled the image as a network, then we shall provide a formal graph-based definition of image segmentation. Consequently image segmentation can be viewed as a partition of the set of pixels with some properties [7,8]. …”

Section: Node-based Segmentationmentioning

confidence: 99%

“…In [7,8], some covering, connectivity and redundancy properties has been studied in relation with a set of fuzzy regions R 1 , . .…”

Section: Introductionmentioning

confidence: 99%

A fuzzy edge-based image segmentation approach

Guada¹,

Gómez²,

Rodríguez³

et al. 2015

Proceedings of the 2015 Conference of the International Fuzzy Systems Association and the European Society for Fuzzy Logic and

View full text Add to dashboard Cite

In this paper, we present a way to define the concept of fuzzy image segmentation, which has not been clearly defined in the literature. In this work the term Fuzzy image segmentation is characterized by means of a fuzzy set over the set of edges, which can be understood as the fuzzy boundary of the image. Also we discuss a visualization of an image segmentation in terms of edge detection. But first, we define two concepts of crisp image segmentation on an image network, one based on nodes and the other one focusing on edges.

show abstract

Fuzzy classification systems

Cited by 102 publications

References 26 publications

A Coloring Algorithm for Image Classification

A Coloring Algorithm for Image Classification

Paired Structures and other opposites-based models

A fuzzy edge-based image segmentation approach

Contact Info

Product

Resources

About