Using a combination of spectral and textural data to measure water-holding capacity in fresh chicken breast fillets

Authors: JIA, BEIBEI - China Agricultural University; WANG, WEI - China Agricultural University; Yoon, Seung-Chul; Zhuang, Hong; LI, YU-FENG - Chinese Academy Of Sciences

Submitted to: Applied Sciences
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 2/22/2018
Publication Date: 2/28/2018
Citation: Jia, B., Wang, W., Yoon, S.C., Zhuang, H., Li, Y. 2018. Using a combination of spectral and textural data to measure water-holding capacity in fresh chicken breast fillets. Applied Sciences. 8(3), p.343.

Interpretive Summary: Water-holding capacity (WHC) is a critical parameter characterizing the quality of meat including chicken meat. The WHC indicates the ability of muscle to retain its inherent or added water. The current industry standard to measure the WHC of individual chicken breast fillets is based on the use of laboratory equipment, which is off-line, destructive, and time-consuming. Thus, there is a great value if a non-contact and non-destructive sensing technique is developed to measure the WHC of individual chicken fillets while they are processed in the processing plants. Hyperspectral imaging (HSI) is an emerging non-contact and non-destructive sensing method for assessing various food attributes. The research team has showed the feasibility of HSI technology to predict the WHC of fresh chicken breast fillets. The objective of the present study was to improve the prediction accuracy of each fillet’s WHC category by combining both spectral and image features with machine learning. Our study found that the performance of the model using both spectral and image features was 86%, which was about 10% improvement in the WHC group prediction over the spectra-only model. The finding suggests that HSI can be used to predict the WHC level of chicken breast meat non-destructively.

Technical Abstract: The aim here was to explore the potential of visible and near-infrared (Vis/NIR) hyperspectral imaging (400–1000 nm) to classify fresh chicken breast fillets into different water-holding capacity (WHC) groups. Initially, the extracted spectra and image textural features, as well as the mixed data of the two, were used to develop partial least square-discriminant analysis (PLS-DA) classification models. Smoothing, a first derivative process, and principle component analysis (PCA) were carried out sequentially on the mean spectra of all samples to deal with baseline offsets and identify outlier data. Six samples located outside the confidence ellipses of 95% confidence level in the score plot were defined as outliers. A PLS-DA model based on the outlier-free spectra provided a correct classification rate (CCR) value of 78% in the prediction set. Then, seven optimal wavelengths selected using a successive projections algorithm (SPA) were used to develop a simplified PLS-DA model that obtained a slightly reduced CCR with a value of 73%. Moreover, the gray-level co-occurrence matrix (GLCM) was implemented on the first principle component image (with 98.13% of variance) of the hyperspectral image to extract textural features (contrast, correlation, energy, and homogeneity). The CCR of the model developed using textural variables was less optimistic with a value of 59%. Compared to results of models based on spectral or textural data individually, the performance of the model based on the mixed data of optimal spectral and textural features was the best with an improved CCR of 86%. The results showed that the spectral and textural data of hyperspectral images together can be integrated in order to measure and classify the WHC of fresh chicken breast fillets.