Measuring water holding capacity in pork meat images using deep learning.

Journal: Meat science
PMID:

Abstract

Water holding capacity (WHC) plays an important role when obtaining a high-quality pork meat. This attribute is usually estimated by pressing the meat and measuring the amount of water expelled by the sample and absorbed by a filter paper. In this work, we used the Deep Learning (DL) architecture named U-Net to estimate water holding capacity (WHC) from filter paper images of pork samples obtained using the press method. We evaluated the ability of the U-Net to segment the different regions of the WHC images and, since the images are much larger than the traditional input size of the U-Net, we also evaluated its performance when we change the input size. Results show that U-Net can be used to segment the external and internal areas of the WHC images with great precision, even though the difference in the appearance of these areas is subtle.

Authors

  • Vinicius Clemente de Sousa Reis
    School of Computer Science, Federal University of Uberlândia (UFU), Uberlândia, MG, Brazil.
  • Isaura Maria Ferreira
    Federal Institute of Triângulo Mineiro, Uberlândia, MG, Brazil. Electronic address: isaura@iftm.edu.br.
  • Mariah Castro Durval
    School of Veterinary Medicine, Federal University of Uberlândia, Uberlândia, MG, Brazil.
  • Robson Carlos Antunes
    School of Veterinary Medicine, Federal University of Uberlândia, Uberlândia, MG, Brazil. Electronic address: robson.antunes@ufu.br.
  • André Ricardo Backes
    Faculty of Computing (FACOM), Federal University of Uberlândia (UFU), Uberlândia, MG, Brazil.