Rapid and non-destructive identification of water-injected beef samples using multispectral imaging analysis

卷:190

Liu, Jinxia ; Cao, Yue ; Wang, Qiu ; Pan, Wenjuan ; Ma, Fei ; Liu, Changhong ; Chen, Wei ; Yang, Jianbo ; Zheng, Lei

Hefei Univ Technol

关键词: Multispectral imaging;    Water-injected beef;    Partial least squares regression;    Feature information;    Non-destructive analysis;   

DOI  :  10.1016/j.foodchem.2015.06.056

学科分类：食品科学和技术

【 摘 要 】

Water-injected beef has aroused public concern as a major food-safety issue in meat products. In the study, the potential of multispectral imaging analysis in the visible and near-infrared (405-970 nm) regions was evaluated for identifying water-injected beef. A multispectral vision system was used to acquire images of beef injected with up to 21% content of water, and partial least squares regression (PLSR) algorithm was employed to establish prediction model, leading to quantitative estimations of actual water increase with a correlation coefficient (r) of 0.923. Subsequently, an optimized model was achieved by integrating spectral data with feature information extracted from ordinary RGB data, yielding better predictions (r = 0.946). Moreover, the prediction equation was transferred to each pixel within the images for visualizing the distribution of actual water increase. These results demonstrate the capability of multispectral imaging technology as a rapid and non-destructive tool for the identification of water-injected beef. (C) 2015 Elsevier Ltd. All rights reserved.