Feasibility of combining spectra with texture data of multispectral imaging to predict heme and non-heme iron contents in pork sausages. (1st January 2016)

• Record Type: Journal Article
• Authors: Ma, Fei; Qin, Hao; Shi, Kefu; Zhou, Cunliu; Chen, Conggui; Hu, Xiaohua; Zheng, Lei
• Is Part Of: Food chemistry. Volume 190(2016)
• Page Start: 142
• Page End: 149
• Publication Date: 2016-01-01
• Subjects: MSI multispectral imaging -- PS pork sausage -- PSs pork sausages -- PLSR partial least squares regression -- Lib-SVM Lib support vector machine -- ROI region of interest -- R2 coefficient of determination -- SE standard error -- SEC standard error of calibration -- SEP standard error of prediction -- SPA successive projections algorithm; Multispectral imaging -- Heme iron -- Non-heme iron -- Pork sausage -- Texture -- Visualization; Food -- Analysis -- Periodicals; Food -- Composition -- Periodicals; 664
• DOI: 10.1016/j.foodchem.2015.05.084
• Languages: English
• ISSNs: 0308-8146

Abstract

Highlights: Multispectral imaging technology could rapidly detect heme and non-heme iron contents in pork sausages. The combination of spectral and textural features could improve precision of predicting heme and non-heme iron contents. Distribution of heme and non-heme iron contents was successfully visualized by image processing and analysis. Abstract: To precisely determine heme and non-heme iron contents in meat product, the feasibility of combining spectral with texture features extracted from multispectral imaging data (405–970 nm) was assessed. In our study, spectra and textures of 120 pork sausages (PSs) treated by different temperatures (30–80 °C) were analyzed using different calibration models including partial least squares regression (PLSR) and LIB support vector machine (Lib-SVM) for predicting heme and non-heme iron contents in PSs. Based on a combination of spectral and textural features, optimized PLSR models were obtained with determination coefficient ( R 2 ) of 0.912 for heme and of 0.901 for non-heme iron prediction, which demonstrated the superiority of combining spectra with texture data. Results of satisfactory determination and visualization of heme and non-heme iron contents indicated that multispectral imaging could serve as a feasible approach for online industrial applications in the future.