Rapid and non-destructive determination of drip loss and pH distribution in farmed Atlantic salmon (Salmo salar) fillets using visible and near-infrared (Vis–NIR) hyperspectral imaging

•Hyperspectral imaging was used to determine drip loss and pH in salmon fillets.•The predictive abilities of PLSR models with two spectral ranges were compared.•Important wavelengths were selected to reduce redundancy of hyperspectral images.•Multivariate models were built for predicting drip loss and pH with good accuracy.•We developed image processing algorithm to obtain drip loss and pH distribution maps. Drip loss and pH are important indices in quality assessment of salmon products. This work was carried out for rapid and non-destructive determination of drip loss and pH distribution in salmon fillets using near-infrared (Vis–NIR) hyperspectral imaging. Hyperspectral images were acquired for salmon fillet samples and their spectral signatures in the 400–1700nm range were extracted. Partial least square regression (PLSR) was used to correlate the spectra with reference drip loss and pH values. Important wavelengths were selected using the regression coefficients method to develop new PLSR models, leading to a correlation coefficient of cross-validation (rCV) of 0.834 with root-mean-square errors by cross-validation (RMSECV) of 0.067 for drip loss and a rCV of 0.877 with RMSECV of 0.046 for pH, respectively. Distribution maps of drip loss and pH were generated based on the new PLSR models using image processing algorithms. The results showed that Vis–NIR hyperspectral imaging technique combined with PLSR calibration analysis offers an effective quantitative capability for determining the spatial distribution of drip loss and pH in salmon fillets.