Skip to main content
ARS Home » Midwest Area » East Lansing, Michigan » Sugarbeet and Bean Research » Research » Publications at this Location » Publication #156626

Title: PREDICTION OF APPLE FRUIT FIRMNESS BY NEAR-INFRARED MULTISPECTRAL SCATTERING

Author
item Lu, Renfu

Submitted to: Journal of Texture Studies
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/31/2004
Publication Date: 7/1/2004
Citation: Lu, R. 2004. Prediction of apple fruit firmness by near-infrared multispectral scattering. Journal of Texture Studies. (35)3:263-276.

Interpretive Summary: Technologies that can grade and sort fruit for internal quality such as firmness, sugar, and acid would greatly enhance the U.S. fruit industry's ability to meet consumer increasing demands for fruit quality and compete in the global marketplace. The objective of this research was to develop an improved multispectral imaging system for real time acquisition of spectral scattering images from apple fruit at discrete wavelengths simultaneously to predict fruit firmness. The multispectral imaging system was assembled and tested with Red Delicious apples. Computer algorithms were developed to analyze light scattering characteristics and relate them to fruit firmness. The multispectral imaging system was able to predict fruit firmness with the correlation coefficient of 0.76 and the standard error of 6.1 N. This research demonstrated that the multispectral imaging system is capable for real time sensing of fruit firmness. The technique is nondestructive and rapid, and can be easily adapted to the existing packing facilities for sorting and grading fruit for firmness. This would provide the fruit industry with a means to deliver superior quality and consistent fresh fruit to the marketplace.

Technical Abstract: Firmness is a key quality attribute in determining the acceptability of apple fruit to the consumer. The objective of this research was to develop and evaluate an improved multispectral imaging system for real time acquisition of scattering images from apple fruit to predict firmness. 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 one-dimensional spectral scattering profiles by radial averaging, which were then input into a backpropagation neural network for predicting apple fruit firmness. It was found that 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 6.1 N for the validation samples.