RT info:eu-repo/semantics/article
T1 Ornamental Potential Classification and Prediction for Pepper Plants (Capsicum spp.): A Comparison Using Morphological Measurements and RGB Images as Data Source
A1 Nascimento, Antonia Maiara Marques do
A1 Ruiz González, Rubén
A1 Martínez-Martínez, Víctor
A1 Medeiros, Artur Mendes
A1 Santos, Fábio Sandro dos
A1 Rêgo, Elizanilda Ramalho do
A1 Pimenta, Samy
A1 Sudré, Cláudia Pombo
A1 Bento, Cintia dos Santos
A1 Cambra Baseca, Carlos
A1 Barroso, Priscila Alves
K1 Ornamental plants
K1 RGB image analysis
K1 Vision Transformer (ViT)
K1 XGBoost
K1 Morphological measurements
K1 Plant breeding
K1 Phenotypic prediction
K1 Pimientos (Plantas)
K1 Peppers
AB Anticipating the ornamental quality of plants is of significant importance for genetic breedingprograms. This study investigated the potential of predicting and classifying whetherornamental pepper plants will exhibit desirable ornamental traits based on RGB images,comparing these results with an approach relying on morphological measurements. Toachieve this, pepper plants from fifteen accessions were cultivated, and photographs weretaken weekly throughout their growth cycle until fruit maturation. A Vision Transformer(ViT)-based model was employed to predict the suitability of the plants for ornamental purposes,and its predictions were validated against assessments conducted by eight experts.An XGBoost-based classifier was employed as well for estimations based on morphological measurements with an accuracy over 92%. The results showed that the ornamental suitabilityof plants can be accurately estimated and predicted up to seven weeks in advance fromphotos, with accuracy over 80%. Interestingly, higher-resolution RGB images did not significantlyimprove the accuracy of the ViT model. Furthermore, the estimation of ornamentalpotential using morphological measurements and RGB images yielded similar accuracy,indicating that a single photograph can effectively replace costly and time-consumingmorphological measurements. As far as the authors are aware, this work is the first toforecast the ornamental potential of pepper plants (Capsicum spp.) multiple weeks aheadof time using image-based deep learning models.
PB MDPI
SN 2076-3417
YR 2025
FD 2025-07
LK https://hdl.handle.net/10259/10875
UL https://hdl.handle.net/10259/10875
LA eng
NO This research was funded by CNPq (Conselho Nacional de Desenvolvimento Cient\u00EDfico e Tecnol\u00F3gico), grant number 408444/2021-5
DS Repositorio Institucional de la Universidad de Burgos
RD 07-may-2026