Skip to main content
ARS Home » Southeast Area » Athens, Georgia » U.S. National Poultry Research Center » Quality & Safety Assessment Research » Research » Publications at this Location » Publication #345762

Research Project: Assessment and Improvement of Poultry Meat, Egg, and Feed Quality

Location: Quality & Safety Assessment Research

Title: Application of VNIR hyperspectral imaging for non-destructive prediction of pH, color, and drip loss of chicken breast fillets

item JIA, BEIBEI - China Agricultural University
item Yoon, Seung-Chul
item Zhuang, Hong
item WANG, WEI - China Agricultural University
item YANG, YI - China Agricultural University
item JIANG, HONGZHE - China Agricultural University
item CHU, XUAN - China Agricultural University
item ZHAO, XIN - China Agricultural University
item KIMULI, DANIE - China Agricultural University

Submitted to: ASABE Annual International Meeting
Publication Type: Proceedings
Publication Acceptance Date: 7/7/2017
Publication Date: 7/24/2017
Citation: Jia, B., Yoon, S.C., Zhuang, H., Wang, W., Yang, Y., Jiang, H., Chu, X., Zhao, X., Kimuli, D. 2017. Application of VNIR hyperspectral imaging for non-destructive prediction of pH, color, and drip loss of chicken breast fillets. ASABE Annual International Meeting. doi:10.13031/aim.201700733.

Interpretive Summary: As one of the world's most popular meat, chicken is considered an important part of healthy diets and has reached a high level of consumption worldwide. In recent years, consumers have paid more and more attention to the quality and safety issues of food. It's important for chicken processing enterprises to provide chicken and chicken production that can meet consumers' demand, as it will directly affect the profitability of enterprises. Color is an important factor that will influence consumers' choice directly. Increases in drip loss and great changes in pH could affect sensory quality attributes, like tenderness, juiciness, and flavor. Traditional detection methods for meat color, drip loss, and pH are usually destructive, time-consuming and laborious. Near infrared (NIR) spectrum technology is a rapid, nondestructive testing technology, and can provide complete information on the chemical constituents which make it a suitable tool for evaluating foods. But one of the disadvantages of NIR spectroscopy is that it cannot apply the spatial information of non-homogeneous samples. Although UV/Vis imaging technique can show the spatial distribution of the whole sample, lack of spectral information makes it very weak in detecting intrinsic chemical components. Thus, hyperspectral imaging (HIS) technique, as one of the novel techniques that can provide the spectral and spatial information simultaneously, has been investigated for fast and reliable meat quality assessment. The prime focus of this study was to explore the performance of VNIR hyperspectral imaging in predicting pH, L*, and drip loss of chicken breast fillets. Our results show that with a PLSR model based on full wavelengths, the hyperspectral imaging prediction of pH, L* values, and drip loss of fresh chicken breast meat varies with data pre-treatment methods and are acceptable. The PLSR models based on the selected wavelengths performs better. This study demonstrates HSI could be used to non-destructively and rapidly predict quality of chicken breast fillets.

Technical Abstract: Non-destructive and rapid prediction of quality attributes of chicken breast fillets using visible and near-infrared (VNIR) hyperspectral imaging (400-1000 nm) was carried out in this work. All hyperspectral images were acquired for bone (dorsal) side of chicken breast. A forward principal component analysis (PCA) and its reverse rotation was firstly conducted to reduce noises and multicollinearity. A band threshold method was adopted on PC1 score image to get the region of interest (ROI) of each sample, then the average reflective spectra of ROI of each image were acquired by reverse PCA rotation. Partial least square regression (PLSR) was utilized to correlate the spectra with measured pH, L* and drip loss values. Informative wavelengths were selected using competitive adaptive reweighed sampling (CARS) to build new PLSR models. Better results were acquired with determination coefficient of prediction ''''''''2/RPD of 0.75/1.86, 0.85/2.52 and 0.68/1.69 for pH, L* and drip loss, respectively. Distribution maps of pH, L* and drip loss were generated based on the improved PLSR models. The results demonstrated that VNIR hyperspectral imaging technique can be used to predict quality attributes of chicken breast fillets.