This paper reports on the measurement of optical property mapping of apples at the wavelengths of 460, 527, 630, and 710 nm using spatial-frequency domain imaging (SFDI) technique, for assessing the soluble solid content (SSC), firmness, and color parameters. A laboratory-based multispectral SFDI system was developed for acquiring SFDI of 140 "Golden Delicious" apples, from which absorption coefficient (μ a ) and reduced scattering coefficient (μ s ') mappings were quantitatively determined using the three-phase demodulation coupled with curve-fitting method. There was no noticeable spatial variation in the optical property mapping based on the resulting effect of different sizes of the region of interest (ROI) on the average optical properties. Support vector machine (SVM), multiple linear regression (MLR), and partial least square (PLS) models were developed based on μ a , μ s ' and their combinations (μ a × μ s ' and μ eff ) for predicting apple qualities, among which SVM outperformed the best. Better prediction results for quality parameters based on the μ a were observed than those based on the μ s ', and the combinations further improved the prediction performance, compared to the individual μ a or μ s '. The best prediction models for SSC and firmness parameters [slope, flesh firmness (FF), and maximum force (Max.F)] were achieved based on the μ a × μ s ', whereas those for color parameters of b* and C* were based on the μ eff , with the correlation coefficients of prediction as 0.66, 0.68, 0.73, 0.79, 0.86, and 0.86, respectively.
Keywords: apple; correlation; optical property mapping; prediction; quality; spatial-frequency domain imaging.
Copyright © 2022 Peng, Zhang, Sun, Sun, Hu, Yang and Wang.