Distance Transformations Based on Ordered Weighted Averaging Operators
| Autor: | López Molina, Carlos, Miguel Turullols, Laura de, Iglesias Rey, Sara, Bustince Sola, Humberto, Baets, Bernard de |
|---|---|
| Přispěvatelé: | Universidad Pública de Navarra. Departamento de Estadística, Informática y Matemáticas, Nafarroako Unibertsitate Publikoa. Estatistika, Informatika eta Matematikak Saila |
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | Academica-e. Repositorio Institucional de la Universidad Pública de Navarra instname |
| ISSN: | 2572-6862 |
| Popis: | Binary image comparison has been a study subject for a long time, often rendering in context-specific solutions that depend upon the type of visual contents in the binary images. Distance transformations have been a recurrent tool in many of such solutions. The literature contains works on the generation and definition of distance transformations, but also on how to make a sensible use of their results. In this work, we attempt to solve one of the most critical problems in the application of distance transformations to real problems: their oversensitivity to certain spurious pixels which, even if having a minimal visual impact in the binary images to be compared, may have a severe impact on their distance transforms. With this aim, we combine distance transformations with Ordered Weighted Averaging (OWA) operators, a well-known information fusion tool from Fuzzy Set Theory. The authors gratefully acknowledge the financial support of the Spanish Research Agency, project PID2019-108392GB-I00 (AEI/10.13039/501100011033), as well as that by Navarra de Servicios y Tecnologías (Nasertic). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|