Jump to main content
Jump to site search


NIR hyperspectral imaging with multivariate analysis for measurement of oil and protein content in peanut varieties

Abstract

The potential of hyperspectral imaging in the spectral range of 1000-2500 nm with multivariate analysis for prediction of oil and protein concentration in five peanut cultivars was investigated. Quantitative partial least squares regression (PLSR) models were established using the extracted spectral data from hyperspectral images and the reference measured oil and protein concentration. The PLSR models established using the whole spectral data pretreated by multiplicative scatter correction (MSC) method showed good results for predicting oil concentration with the determination coefficient (R2P) of 0.945 and root mean square errors by prediction (RMSEP) of 0.196, and for predicting protein concentration with R2P of 0.901 and RMSEP of 0.441. In addition, eight and eight optimal wavelengths were selected using the regression coefficients of the PLSR analysis and used for simplifying the obtained models. The simplified PLSR models also presented good performances with R2p of 0.933 and 0.912 for predicting oil and protein concentration. The whole results demonstrated that NIR hyperspectral imaging technique coupled with chemometrics analysis is a promising tool for rapid and non-destructive determination of oil and protein concentration in peanut kernels and has the potential to develop a multispectral imaging system for future on-line detection of peanut quality.

Back to tab navigation

Publication details

The article was received on 03 Sep 2017, accepted on 25 Sep 2017 and first published on 02 Oct 2017


Article type: Paper
DOI: 10.1039/C7AY02115A
Citation: Anal. Methods, 2017, Accepted Manuscript
  •   Request permissions

    NIR hyperspectral imaging with multivariate analysis for measurement of oil and protein content in peanut varieties

    H. Jin, J. Cheng, Z. Xu and F. Zheng, Anal. Methods, 2017, Accepted Manuscript , DOI: 10.1039/C7AY02115A

Search articles by author

Spotlight

Advertisements