Skip to main content
ARS Home » Midwest Area » East Lansing, Michigan » Sugarbeet and Bean Research » Research » Publications at this Location » Publication #165769


item Lu, Renfu

Submitted to: ASAE Annual International Meeting
Publication Type: Proceedings
Publication Acceptance Date: 7/1/2004
Publication Date: 8/4/2004
Citation: Lu, R., Peng, Y. 2004. Hyperspectral scattering for assessing peach fruit firmness. ASAE Annual International Meeting. Paper No. 046117.

Interpretive Summary: Firmness is an important parameter in determining the overall eating quality of peach fruit and their storage life and consumer acceptance. Nondestructive sensing of peach fruit firmness will enable the fruit industry to better manage harvest time and implement more appropriate postharvest handling and storage procedures for delivering better quality fruit to the marketplace. This research investigated a hyperspectral imaging technique to acquire scattering profiles from peaches for predicting fruit firmness. Hyperspectral imaging is a technique with the capability of acquiring both spectral and spatial information from an object. A newly developed hyperspectral imaging system was used to acquire spectral scattering profiles from peach fruit over the wavelengths between the visible and short wave near-infrared region. With the use of a mathematical model and the artificial neural network method, good firmness predictions were obtained with the correlation coefficient of 0.90. This research demonstrated that hyperspectral imaging is useful for predicting peach fruit firmness. The technique is nondestructive and rapid, and it is promising for nondestructive grading of peach fruit for firmness. The technique will help the fruit industry in assuring the quality and consistency of peach fruit for domestic and international markets.

Technical Abstract: Firmness is an important attribute in determining the overall eating quality of peach fruit. The objective of this research was to investigate the potential of using hyperspectral scattering to predict peach fruit firmness. A hyperspectral imaging system was used to acquire scattering images from 'Red Haven' peaches over the spectral region between 500 nm and 1040 nm. A Lorentzian function with two parameters was proposed to describe the scattering profiles of peach fruit. Principal component (PC) analysis was performed on spectra of the two Lorentzian parameters and their product. A backpropagation feedforward neural network, with inputs of PC scores from parameter spectra, was developed for predicting fruit firmness. Among the three spectra, the product of the Lorentzian parameters gave best firmness predictions with r=0.90 and the standard error for validation of 12.07 N. Hyperspectral scattering is useful for assessing the firmness of peach fruit.