Rapid on-line detection and grading of wooden breast myopathy in chicken fillets by near-infrared spectroscopy.
Ontology highlight
ABSTRACT: The main objective of this work was to develop a method for rapid and non-destructive detection and grading of wooden breast (WB) syndrome in chicken breast fillets. Near-infrared (NIR) spectroscopy was chosen as detection method, and an industrial NIR scanner was applied and tested for large scale on-line detection of the syndrome. Two approaches were evaluated for discrimination of WB fillets: 1) Linear discriminant analysis based on NIR spectra only, and 2) a regression model for protein was made based on NIR spectra and the estimated concentrations of protein were used for discrimination. A sample set of 197 fillets was used for training and calibration. A test set was recorded under industrial conditions and contained spectra from 79 fillets. The classification methods obtained 99.5-1
SUBMITTER: Wold JP
PROVIDER: S-EPMC5344484 | biostudies-literature | 2017
REPOSITORIES: biostudies-literature
ACCESS DATA