Skip to main content
ARS Home » Southeast Area » Athens, Georgia » U.S. National Poultry Research Center » Quality and Safety Assessment Research Unit » Research » Publications at this Location » Publication #350506
Research Project: Assessment and Improvement of Poultry Meat, Egg, and Feed Quality

Location: Quality and Safety Assessment Research Unit

Title: Visible and near-infrared hyperspectral imaging for cooking loss classification of fresh broiler breast fillets

Author
item JIANG, HONGZHE - China Agricultural University
item WANG, WEI - China Agricultural University
item Zhuang, Hong
item Yoon, Seung-Chul
item LI, YUFENG - China Agricultural University

Submitted to: Applied Sciences
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 1/28/2018
Publication Date: 2/1/2018
Citation: Jiang, H., Wang, W., Zhuang, H., Yoon, S.C., Li, Y. 2018. Visible and near-infrared hyperspectral imaging for cooking loss classification of fresh broiler breast fillets. Applied Sciences. doi:10.3390/app8020256.
DOI: https://doi.org/10.3390/app8020256

Interpretive Summary: Cooking loss is one of the most important quality attributes of meat products. Cooking loss directly affects the yield of further-processed cooked meat and is negatively related with eating quality of finished products, such as juiciness. Thus, knowing meat cooking loss will benefit meat processors and product acceptance by consumers. Traditionally, cooking loss is measured as weight differences (as a percentage) before and after cooking. Although it can provide direct information about cooking loss, the method is laborious, time-consuming, invasive, and must be conducted on the basis of cooked meat. Therefore, the development of a rapid and non-destructive technique to assess meat cooking loss could interest the industry. Hyperspectral imaging (HIS) is an emerging technology, which can rapidly and non-destructive predict quality of food products. Recently, considerable endeavors have been made in meat research and proved that HSI can successfully predict quality of pork, beef, lamb, and fish. Therefore, the objective of in this study was to investigate the potential to use visible and near-infrared HSI to assess cooking loss of fresh broiler breast fillets. Our results show that fresh broiler breast meat could be classified into high cooking loss and low cooking loss groups based on multivariate analyses of HIS data. Prediction results based on full spectra are comparable with those based on 18 dominant wavelengths, indicating that either spectrum can be used for the prediction. The classification maps based on data analyses successfully show visual differences in cooking loss between high cooking loss and low cooking loss chicken breast fillets. These results suggest that the HSI is a promising tool for rapid and non-destructive prediction of cooking loss of fresh chicken breast meat.

Technical Abstract: Cooking loss (CL) is a critical quality attribute directly relating to meat juiciness. The potential of the hyperspectral imaging (HSI) technique was investigated for non-invasively classifying and visualizing the CL of fresh broiler breast meat. Hyperspectral images of total 75 fresh broiler breast fillets were acquired by the system operating in the visible and near-infrared (VNIR, 400–1000 nm) range. Mean spectra were extracted from regions of interest (ROIs) determined by pure muscle tissue pixels. CL was firstly measured by calculating the weight loss in cooking, and then fillets were grouped into high-CL and low-CL according to the threshold of 20%. The classification methods partial least square-discriminant analysis (PLS-DA) and radial basis function-support vector machine (RBF-SVM) were applied, respectively, to determine the optimal spectral calibration strategy. Results showed that the PLS-DA model developed using the data, that is, first-order derivative (Der1) of VNIR full spectra, performed best with correct classification rates (CCRs) of 0.90 and 0.79 for the calibration and prediction sets, respectively. Furthermore, to simplify the optimal PLS-DA model and make it practical, effective wavelengths were individually selected using uninformative variable elimination (UVE) and competitive adaptive reweighted sampling (CARS). Through performance comparison, the CARS-PLS-DA combination was identified as the optimal method and the PLS-DA model built with 18 informative wavelengths selected by CARS resulted in good CCRs of 0.86 and 0.79. Finally, classification maps were created by predicting CL categories of each pixel in the VNIR hyperspectral images using the CARS-PLS-DA model, and the general CL categories of fillets were readily discernible. The overall results were encouraging and showed the promising potential of the VNIR HSI technique for classifying fresh broiler breast fillets into different CL categories.