Early identification of mushy Halibut syndrome with hyperspectral image analysis

• DOI: 10.1016/j.lwt.2023.114559
• Publication Date: 2023-02-04T10:34:07Z
• Authors: Samuel Ortega; Stein-Kato Lindberg; Stein Harris Olsen; Kathryn E. Anderssen; Karsten Heia
• Keywords: Identification

Mushy Halibut Syndrome (MHS) is a condition that appears in Greenland halibut and manifests itself as abnormally opaque, flaccid jelly-like flesh. Fish affected by this syndrome show poor meat quality, which results negative consequences for the fish industry. The research community has not carefully investigated condition, nor novel technologies MHS detection have been proposed. In work, we propose using hyperspectral imaging to detect MHS. After collecting dataset of images MHS, two different goals were targeted. Firstly, estimation chemical composition samples (specifically fat water content) from their spectral data constrained unmixing. Secondly, supervised classification partial least squares discriminant analysis (PLS-DA) was evaluated identify specimens outcomes our study suggest prediction possible, but content found be accurate. However, PLS-DA precise both fillets whole fish, with lower bounds 75% 83% precision recall, respectively. Our findings suitable technology early screening