Prediction of apple fruit firmness by near-infrared multispectral scattering

The objective of this research was to predict fruit firmness by developing and evaluating a multispectral imaging system for real time acquisition of scattering images from apple fruit. A circular broadband light beam was used to generate light backscattering at the surface of apple fruit and scattering images were acquired, using a common aperture multispectral imaging system, from Red Delicious apple fruit for wavelengths at 680, 880, 905, and 940 nm. Scattering images were reduced to produce one-dimensional spectral scattering profiles by radial averaging, which were then input into a backpropagation neural network for predicting apple fruit firmness. The neural network performed best when 10 neurons and 20 epochs were used. With three ratios of spectral profiles involving all four wavelengths, the neural network gave firmness predictions with the correlation of 0.76 and the standard error of 6.2 N for the validation samples.