Hyperspectral image-based multi-feature integration for TVB-N measurement in pork

• Published in: Journal of food engineering 2018-02, Vol.218, p.61-68
• Main Authors: Guo, Tengfei, Huang, Min, Zhu, Qibing, Guo, Ya, Qin, Jianwei
• Format: Article
• Language: English
• Subjects: Gabor filter; Hyperspectral imaging; Nondestructive detection; Total volatile basic nitrogen; Two-dimensional principal component analysis
• ISSN: 0260-8774; 1873-5770
• DOI: 10.1016/j.jfoodeng.2017.09.003

Total volatile basic nitrogen (TVB-N) content is an important index used to evaluate the freshness of pork. In this paper, a strategy for measurement of TVB-N content in pork through hyperspectral imaging (HSI) (400–1000 nm) was developed. Firstly, image textural features based on Gabor filter and spectral features were obtained from the hyperspectral image after determining the region of interest. Then, nine feature wavelengths were selected using partial least-squares projection algorithm. And, major components were obtained from the 2D principal component analysis (2DPCA). Finally, a calibration model was established based on major components using least-squares support vector machine to predict TVB-N values. The results of two methods for data fusion, which are 2DPCA and principal component analysis (PCA), are compared. The correlation coefficients of prediction (RP) and root-mean-square errors of prediction (RMSEP) obtained through 2DPCA were 0.955 and 1.86 mg/100 g respectively, which was superior to the results based on PCA (RP = 0.944, RMSEP = 2.07 mg/100 g). Compared to PCA, the residual prediction deviations (RPD) based on 2DPCA was raised from 3.01 to 3.35. Results demonstrated that the proposed model based on 2DPCA exhibited potential for nondestructive detection of TVB-N content in pork. •Pork freshness was detected by hyperspectral imaging system.•Six characteristics were acquired from hyperspectral images.•Major components were obtained using two-dimensional principal component analysis.•The prediction models using major components achieved good prediction accuracy.