A novel ground truth multispectral image dataset with weight, anthocyanins, and Brix index measures of grape berries tested for its utility in machine learning pipelines
Ver/
Compartir
Estadísticas
Ver Estadísticas de usoMetadatos
Mostrar el registro completo del ítemAutor
Navarro Lorente, Pedro Javier; Miller, Leanne Rebecca; Díaz Galián, Victoria; Gila Navarro, Alberto; Águila, Diego J.; [et al.]Grupo de investigación
Division de Sistemas e Ingeniería Electrónica (DSIE)Fundación SénecaÁrea de conocimiento
Lenguajes y Sistemas InformáticosPatrocinadores
This research was funded by Ministerio de Ciencia e Innovacion, BFU 2017–88300-C2-1-R to Marcos Egea-Cortines, BFU 2017–88300-C2-2-R and Horecov-21 to Pedro J. Navarro, CDTI 5117/17CTA-P to Marcos Egea-Cortines, and the “Research Programme for Groups of Scientific Excellence in the Region of Murcia” of the Seneca Foundation (Agency for Science and Technology in the Region of Murcia—19895/GERM/15). There is no local legislation concerning the acquisition of images from grape berries.Fecha de publicación
2022-10Editorial
Oxford University PressCita bibliográfica
Pedro J Navarro, Leanne Miller, María Victoria Díaz-Galián, Alberto Gila-Navarro, Diego J Aguila, Marcos Egea-Cortines, A novel ground truth multispectral image dataset with weight, anthocyanins, and Brix index measures of grape berries tested for its utility in machine learning pipelines, GigaScience, Volume 11, 2022, giac052, https://doi.org/10.1093/gigascience/giac052Revisión por pares
siPalabras clave
Ground truthGrape
Computer vision
Multispectral
Machine learning
Resumen
The combination of computer vision devices such as multispectral cameras coupled with artificial intelligence has provided a major leap forward in image-based analysis of biological processes. Supervised artificial intelligence algorithms require large ground truth image datasets for model training, which allows to validate or refute research hypotheses and to carry out comparisons between models. However, public datasets of images are scarce and ground truth images are surprisingly few considering the numbers required for training algorithms.
Colecciones
- Artículos [1768]
Redes sociales