Skip to main content
ARS Home » Midwest Area » East Lansing, Michigan » Sugarbeet and Bean Research » Research » Publications at this Location » Publication #201893

Title: Nondestructive measurement of firmness and soluble solids content for apple fruit using hyperspectral scattering images

Author
item Lu, Renfu

Submitted to: Sensing and Instrumentation for Food Quality and Safety
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/24/2006
Publication Date: 3/2/2007
Citation: Lu, R. 2007. Nondestructive measurement of firmness and soluble solids content for apple fruit using hyperspectral scattering images. Sensing and Instrumentation for Food Quality and Safety. 1(1):19-27.

Interpretive Summary: Firmness and sugar are two important quality parameters in determining maturity or harvest time and postharvest quality of apples. Rapid and nondestructive measurement of these quality parameters would ensure consistent quality fruit. Recently, near-infrared spectroscopy has been used for assessing and grading fruit for soluble solids content or sugar; however the technique is unsatisfactory in assessing fruit firmness. In this research, a hyperspectral imaging technique was developed to acquire spectral scattering images from apple fruit for predicting firmness and soluble solids content. Hyperspectral imaging possesses the main features of imaging and spectroscopy, and it is especially useful for obtaining spectral and spatial information from an object. Spectral scattering images were acquired from two cultivars of apple over the visible and short-wave near-infrared region. A scattering image analysis method incorporating artificial neural networks was used to develop firmness and soluble solids prediction models. Good firmness and soluble solids predictions were obtained for Golden Delicious apples with the correlation coefficient of 0.87 and 0.89, respectively. Lower corrections were obtained for Red Delicious apples. The hyperspectral scattering technique is especially useful for assessing fruit firmness because it enables better characterization of light scattering in the fruit, compared to conventional near-infrared spectroscopy. This new method is fast and relatively easy to implement for rapid measurement of fruit quality. The technique is potentially useful for online sorting and grading of fruit for internal quality, which will help the fruit industry deliver better quality and consistent fruit to the consumer.

Technical Abstract: Nondestructive sensing is critical to assuring postharvest quality of apple fruit and increasing consumer acceptance and satisfaction. The objective of this research was to use a hyperspectral scattering technique to acquire spectral scattering images from apple fruit and to develop a data analysis method relating hyperspectral scattering characteristics to fruit firmness and soluble solids content. A hyperspectral imaging system was used for acquiring hyperspectral scattering images from ‘Golden Delicious’ and ‘Red Delicious’ apples generated by a broadband beam over the spectral region between 500 nm and 1000 nm. Mean and standard deviation spectra were extracted from the hyperspectral scattering images. A hybrid method combining the backpropagation feedforward neural network with principal component analysis was used to predict fruit firmness and soluble solids content. The neural network models were able to predict fruit firmness with r=0.87 and the standard error of prediction (SEP) of 6.2 N for Golden Delicious, and r=0.74 and SEP=6.1 N for Red Delicious. Better SSC predictions were obtained with r = 0.89 and 0.80 and SEP = 0.72% and 0.81% for Golden Delicious and Red Delicious, respectively. Hyperspectral scattering is promising for assessing internal quality, especially the firmness, of apples.