|JIA, BEIBEI - China Agricultural University
|WANG, WEI - US Department Of Agriculture (USDA)
|LI, CHUNYANG - Jiangsu Academy Agricultural Sciences
Submitted to: Journal of Food Engineering
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/23/2017
Publication Date: 3/26/2017
Citation: Jia, B., Zhuang, H., Yoon, S.C., Wang, W., Li, C. 2017. Prediction of pH of fresh chicken breast fillets by VNIR hyperspectral imaging. Journal of Food Engineering. 208:57-65.
Interpretive Summary: pH values have significant influences on the quality of chicken meat, especially chicken breast meat. The standard method for pH measurements of meat is to use a pH meter that is destructive, time-consuming, laborious, and also unsuitable for online meat quality monitoring. This study addressed the following research question: how to rapidly and accurately predict the pH values of raw, fresh chicken breast meat with a non-destructive, non-contact sensing technique. The study adopted an optical image probing technique, called hyperspectral imaging, to detect spectral fingerprint information correlated with overall meat pH values and its spatial distribution within individual fillets without the need for a contact with a sample. The study showed that mathematical models developed with hyperspectral images could well predict overall meat pH values of chicken fillets. In addition, hyperspectral imaging would be able to provide distribution information of pH values within chicken breast.
Technical Abstract: Visible and near-infrared (VNIR) hyperspectral imaging (400–900 nm) was used to evaluate pH of fresh chicken breast fillets (pectoralis major muscle) from the bone (dorsal) side of individual fillets. After the principal component analysis (PCA), a band threshold method was applied to the first principal component (PC1) score image in order to get the region of interest (ROI). Then, the average reflective spectrum of ROI of each image was acquired by inverse PCA transform. Eight pretreatment algorithms were evaluated for partial least squares regression (PLSR) models. The PLSR model with the pretreatment of multiplicative scatter correction followed by second derivative showed the best performance with coefficients of determination for validation (R_v^2) of 0.87, root mean square error for validation (RMSEv) of 0.16 and the ratio of percentage deviation (RPD) of 2.02. Optimal 20 wavelengths were selected using competitive adaptive reweighed sampling (CARS) method to develop a new multispectral PLSR model, leading to an enhanced result with (R_v^2) of 0.94, RMSEv of 0.06 and RPD of 3.55. To assess the performance of the prediction models, new ROIs where pH values were measured using a pH probe, were defined and corresponding mean spectra were used as an independent test set of the new multispectral PLSR model. Coefficients of determination for independent test set (R_p^2) and root mean square error for independent test set (RMSEp) were 0.73 and 0.29, respectively. The prediction image showing the spatial distribution of the predicted pH values was generated to analyze the spatial context of pH values as well as the overall pH level of each fillet. The results demonstrated that VNIR hyperspectral imaging could be used to predict spatial and global pH values of fresh chicken breast meat.