Multispectral imaging for predicting sugar content of 'Fuji' apples. (October 2018)

• Record Type: Journal Article
• Authors: Tang, Chunxiao; He, Hayi; Li, Enbang; Li, Hongqiang
• Is Part Of: Optics & laser technology. Volume 106(2018)
• Page Start: 280
• Page End: 285
• Publication Date: 2018-10
• Subjects: Multispectral imaging -- Wavelength selection -- Camera response function -- Image histogram -- Lorentzian function; Optics -- Periodicals; Lasers -- Periodicals; Electronic journals; 621.366
• DOI: 10.1016/j.optlastec.2018.04.017
• Languages: English
• ISSNs: 0030-3992

Abstract

Highlights: An investigation of using multispectral imaging to predict fruit sugar content is proposed. The optimal wavelengths were selected using the combination of BiPLS and stepwise MLR. Only the scattering areas (SA) of the images were used for prediction. SA was segmented using the image histogram and the camera response function. The MLR model predicted sugar content with r = 0.8861 and RMSE = 0.8738° Brix. Abstract: This research investigated a usage of multispectral imaging to predict sugar content of 'Fuji' apples. A visible/near-infrared spectroscopy (350–1200 nm) was used to select optimal wavelengths for the multispectral imaging system. The spectral data were analyzed using the backward interval partial least square to generate a subset composed of several most sensitive wavebands. Four optimal wavelengths (461 nm, 469 nm, 947 nm and 1049 nm) were determined from this subset using stepwise multiple linear regression. A multispectral imaging system was developed based on these effective wavelengths. The scattering areas of the multispectral images were extracted by using the image histogram and the camera response function. The scattering profiles were calculated from the scattering areas by radial averaging. The modified Lorentzian distribution function was used to fit the scattering profiles. The parameters of the Lorentzian functions were used as the data base of multiple linear regression to create the prediction model. The multiple linear regression model predicted sugar content with r = 0.8861 and RMSE (root-mean-square-error of calibration) = 0.8738° Brix.