Submitted to: Fruit Processing
Publication Type: Trade Journal
Publication Acceptance Date: 7/17/2003
Publication Date: 8/20/2003
Citation: Lu, R. 2003. Imaging spectroscopy for assessing fruit quality. Fruit Processing.
Technical Abstract: Texture and flavor are two important quality components for fresh fruit. Technologies that can nondestructively measure texture and flavor would greatly improve the fruit industry's ability to meet consumer demands for fruit quality and enhance competitiveness in the global marketplace. We conducted an experiment using a novel optical technique for measuring firmness and soluble solids content (SSC) of apple fruit. An imaging spectroscopy system was developed to measure the scattering of light in Golden Delicious and Red Delicious apples over the visible and short-wave near-infrared region (500 nm ' 1,000 nm). The mean, standard deviation, and maximum spectra were obtained from each scattering image. A forward-propagation neural network model with one hidden layer was used to predict firmness and SSC with inputs from the scattering images of apple fruit. Relatively good predictions of apple fruit firmness were obtained with the correlation coefficient of 0.83 and 0.71 and the standard error of prediction of 7.3 N and 6.1 N for Golden Delicious and Red Delicious apples, respectively. Good predictions of SSC were obtained with the correlation coefficient of 0.88 and 0.80 and the standard error of prediction of 0.7 deg and 0.8 deg Brix for Golden Delicious and Red Delicious apples, respectively. The imaging spectroscopy technique is useful for measuring and grading apple fruit for firmness and sugar content.