Servicios Personalizados
Revista
Articulo
Indicadores
- Citado por SciELO
- Accesos
Links relacionados
- Citado por Google
- Similares en SciELO
- Similares en Google
Compartir
TecnoLógicas
versión impresa ISSN 0123-7799versión On-line ISSN 2256-5337
Resumen
SOTO SOGAMOSO, Jimilgton Enrique; PINTO LOPERA, Jesús Emilio y MILLAN ROJAS, Edwin Eduardo. Arbuscular Mycorrhizae and the Computer Vision Techniques for their Identification. TecnoL. [online]. 2022, vol.25, n.54, e302. Epub 28-Oct-2022. ISSN 0123-7799. https://doi.org/10.22430/22565337.2348.
This article aims to analyze the leading computer vision techniques and strategies used in designed systems to automatically identify arbuscular mycorrhizal fungi, addressing general aspects of mycorrhizae and their taxonomic classification. Mycorrhizae are symbiotic associations between plants' roots and certain fungi groups. They are characterized by great benefits to the surrounding soil, the plants, and the derived productive processes. The work was developed with a specialized information collection methodology based on specific search criteria, selecting relevant publications, in a time range between 2014 and 2021, in the Scopus, Scielo, Dialnet, and Google Scholar databases. The study's results revealed that fuzzy mathematical morphology is an essential technique in the segmentation of fungal spores. In general, the studies developed are based on a binary identification of the spores, where the Hough transform, and artificial neural networks are the combined techniques that report better results. This study concludes that it is possible to assist the identification process of mycorrhizal fungi from artificial vision techniques. It contributes by indicating a lack of information regarding non-binary classification systems, which are important and must be considered to support advanced classification processes, according to the number of families and genera reported in the literature.
Palabras clave : Morphometric Classification; Soil Decontamination; Arbuscular Mycorrhizal Fungi; Automatic Identification System; Computer Vision.