Skip to main content
ARS Home » Northeast Area » Kearneysville, West Virginia » Appalachian Fruit Research Laboratory » Innovative Fruit Production, Improvement, and Protection » Research » Publications at this Location » Publication #328389
Title: Non-destructive detection and quantification of blueberry bruising using near-infrared (NIR) hyperspectral reflectance imaging

Author
item YU, JIANG - University Of Georgia
item LI, CHANGYING - University Of Georgia
item Takeda, Fumiomi

Submitted to: Scientific Reports
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 10/4/2016
Publication Date: 10/21/2017
Citation: Yu, J., Li, C., Takeda, F. 2017. Non-destructive detection and quantification of blueberry bruising using near-infrared (NIR) hyperspectral reflectance imaging. Scientific Reports. doi: 10:1038/srep35679.

Interpretive Summary: Currently, blueberry bruising is evaluated by either visual or tactile inspection, or with fruit firmness measuring instruments. These methods are destructive and time-consuming. The goal of this research was to develop a non-destructive approach for blueberry bruising detection and quantification by using near-infrared reflectance imaging technology. The spectra of bruised and healthy tissues were statistically separated, and the separation was independent of cultivars. Support vector machine (SVM) classification of the spectra from the region of interest achieved over 94%, 92%, and 96% accuracy on the training set, independent testing set, and combined set, respectively. The statistical results showed that the bruise ratio was equivalent to the measured firmness but better than the predicted firmness in regard to effectiveness of bruising quantification, and the bruise ratio had a strong correlation with human assessment (R2=0.78-0.83). Therefore, the proposed approach and the bruise ratio index are effective in non-destructive detection and quantification of blueberry bruising.

Technical Abstract: Currently, blueberry bruising is evaluated by either human visual/tactile inspection or firmness measurement instruments. These methods are destructive and time-consuming. The goal of this paper was to develop a non-destructive approach for blueberry bruising detection and quantification. The spectra of bruised and healthy tissues were statistically separated, and the separation was independent of cultivars. Support vector machine (SVM) classification of the spectra from the regions of interests (ROIs) achieved over 94%, 92%, and 96% accuracy on the training set, independent testing set, and combined set, respectively. The statistical results showed that the bruise ratio was equivalent to the measured firmness but better than the predicted firmness in regard to effectiveness of bruising quantification, and the bruise ratio had a strong correlation with human assessment (R2=0.78-0.83). Therefore, the proposed approach and the bruise ratio index are effective to non-destructive detection and quantification of blueberry bruising.