Submitted to: Agricultural Engineering International Conference
Publication Type: Proceedings
Publication Acceptance Date: 5/30/2003
Publication Date: 7/27/2003
Citation: Lu, R. 2003. Imaging spectroscopy for assessing internal quality of apple fruit. Agricultural Engineering International Conference Proceedings. Interpretive Summary: Currently, the fruit industry lacks adequate nondestructive sensing technologies to assess, grade, and sort fruit for internal quality such as firmness, sugar, and acid. Lack of a good method to evaluate quality is a major constraint for the industry to deliver better quality and more consistent fruit to the consumer. Consumer dissatisfaction with quality is a major cause for the staggering consumption of fresh fruit in the U.S. We developed a novel sensing method of imaging spectroscopy to predict internal quality of apple fruit, especially firmness and sweetness. Imaging spectroscopy is a technique that combines the features of imaging and spectroscopy to acquire both spectral and spatial information from an object, thus greatly expanding our capability of detecting some minor or subtle features in the object. The proposed technique was able to predict apple fruit firmness with the correlation coefficient of 0.83 and 0.71 and the prediction error of 7.3 N and 6.1 N for Golden Delicious and Red Delicious apples, respectively. Good predictions of apple sweetness were obtained with the correlation coefficient of 0.88 and 0.81 and the prediction error of 0.80 and 0.81 for Golden Delicious and Red Delicious apples, respectively. This research will lead to the development of a new sensing technology for assessing and sorting apples and other fresh fruits for texture and flavor. The technology will help the U.S. fruit industry gain competitive advantages and improve profitability.
Technical Abstract: Nondestructive sensing of internal quality would allow the fruit industry to deliver better quality, more consistent fruit to the consumer. The objective of this research was to study the feasibility of using an imaging spectroscopy technique to predict the firmness and soluble solid content (SSC) of apple fruit. An imaging spectroscopy system was assembled to acquire scattering images from apple fruit over the spectral region between 500 nm and 1000 nm. Computer algorithms were developed using the neural network method to relate the mean and standard deviation spectra to the firmness and SSC of apple fruit. Preliminary analysis showed that the imaging spectroscopy system was able to predict fruit firmness with r=0.83 and the standard error of prediction (SEP) of 7.3 N for Golden Delicious, and r=0.71 and SEP=6.1 N for Red Delicious. Better SSC predictions were obtained with r = 0.88 and 0.80, and the SEP of 0.72 and 0.81 for Golden Delicious and Red Delicious apples, respectively.