EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting the Body Weight of Tilapia Fingerlings from Images Using Computer Vision

Lessandro do Carmo Lima, Adriano Carvalho Costa, Heyde Francielle do Carmo França, Alene Santos Souza, Gidélia Araújo Ferreira de Melo, Brenno Muller Vitorino, Vitória de Vasconcelos Kretschmer, Suzana Maria Loures de Oliveira Marcionilio, Rafael Vilhena Reis Neto, Pedro Henrique Viadanna, Gabriel Rinaldi Lattanzi, Luciana Maria da Silva und 1 weitere

Fishes · 02.08.2025 · 10 (8) · 371

DOI: 10.3390/fishes10080371 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Fishes, online erschienen am 02.08.2025. Verfasst von Lessandro do Carmo Lima und 12 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: IF Goiano, Goiás State Research Support Foundation (FAPEG), National Council for Scientific and Technological Development (CNPq), Alevinos Rio Verde.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The aim of this study was to develop a mathematical model to predict the body weight of tilapia fingerlings using variables obtained through computer vision. A total of 2092 tilapia fingerlings and juveniles, weighing between 10 and 100 g, were fasted for 12 h, anesthetized, weighed, and photographed using an iPhone 12 Pro Max at 33 cm height in a closed container with different bottom colors. Images were segmented using Roboflow’s instance segmentation model, achieving 99.5% mean average precision, 99.9% precision, and 100% recall. From the segmented images, area, perimeter, major axis (MA), minor axis (SA), X and Y centroids, compactness, eccentricity, and the MA/SA ratio were extracted. Seventy percent of the data was used to build the model, and 30% for validation. Stepwise multiple regression (backward selection) was performed, using body weight as the dependent variable. The prediction model was: −17.7677 + 0.0007539(area) – 0.0848303 (MA) – 0.108338(SA) + 0.0034496(CX). The validation model showed similar coefficients and R2 = 0.99. The second validation, using observed versus predicted values, also yielded an R2 of 0.99 and a mean absolute error of 1.57 g. Correlation and principal component analyses revealed strong positive associations among body weight, area, axes, and predicted values. Computer vision proved effective for predicting tilapia fingerlings’ weight.

Förderung

  • IF Goiano, Goiás State Research Support Foundation (FAPEG)
  • National Council for Scientific and Technological Development (CNPq)
  • Alevinos Rio Verde

Zitieren

APA

Lima, L. D. C., Costa, A. C., França, H. F. D. C., Souza, A. S., Melo, G. A. F. D., Vitorino, B. M., Kretschmer, V. D. V., Marcionilio, S. M. L. D. O., Neto, R. V. R., Viadanna, P. H., Lattanzi, G. R., Silva, L. M. D., & Costa, K. A. D. P. (2025). Predicting the Body Weight of Tilapia Fingerlings from Images Using Computer Vision. Fishes, 10(8), 371. https://doi.org/10.3390/fishes10080371

Vancouver

Lima LDC, Costa AC, França HFDC, Souza AS, Melo GAFD, Vitorino BM, et al. Predicting the Body Weight of Tilapia Fingerlings from Images Using Computer Vision. Fishes. 2025;10(8):371. doi:10.3390/fishes10080371

BibTeX
@article{Lima2025,
  author = {Lima, Lessandro do Carmo and Costa, Adriano Carvalho and França, Heyde Francielle do Carmo and Souza, Alene Santos and Melo, Gidélia Araújo Ferreira de and Vitorino, Brenno Muller and Kretschmer, Vitória de Vasconcelos and Marcionilio, Suzana Maria Loures de Oliveira and Neto, Rafael Vilhena Reis and Viadanna, Pedro Henrique and Lattanzi, Gabriel Rinaldi and Silva, Luciana Maria da and Costa, Kátia Aparecida de Pinho},
  title = {Predicting the Body Weight of Tilapia Fingerlings from Images Using Computer Vision},
  journal = {Fishes},
  year = {2025},
  volume = {10},
  number = {8},
  pages = {371},
  doi = {10.3390/fishes10080371}
}
Kostenlos starten →