(Springer, 2023) Marco Detchart, Cedric; Lucca, Giancarlo; Pereira Dimuro, Graçaliz; Da Cruz Asmus, Tiago; López Molina, Carlos; Borges, Eduardo N.; Rincón Arango, Jaime Andrés; Julian, Vicente; Bustince Sola, Humberto; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika
In this work, we compare different families of fuzzy integrals
in the context of feature aggregation for edge detection. We analyze the
behaviour of the Sugeno and Choquet integral and some of its generalizations.
In addition, we study the influence of the fuzzy measure over
the extracted image features. For testing purposes, we follow the Bezdek
Breakdown Structure for edge detection and compare the different fuzzy
integrals with some classical feature aggregation methods in the literature.
The results of these experiments are analyzed and discussed in
detail, providing insights into the strengths and weaknesses of each approach.
The overall conclusion is that the configuration of the fuzzy measure
does have a paramount effect on the results by the Sugeno integral,
but also that satisfactory results can be obtained by sensibly tuning such
parameter. The obtained results provide valuable guidance in choosing
the appropriate family of fuzzy integrals and settings for specific applications.
Overall, the proposed method shows promising results for edge
detection and could be applied to other image-processing tasks.
