Skip to main content
ARS Home » Northeast Area » Beltsville, Maryland (BARC) » Beltsville Agricultural Research Center » Environmental Microbial & Food Safety Laboratory » Research » Publications at this Location » Publication #280373

Title: Classification of Korla fragrant pears using NIR hyperspectral imaging analysis

item RAO, XIUQIN - Zhejiang University
item Yang, Chun Chieh
item YING, YIBIN - Zhejiang University
item Chao, Kuanglin - Kevin Chao
item Kim, Moon

Submitted to: Proceedings of SPIE
Publication Type: Abstract Only
Publication Acceptance Date: 4/20/2012
Publication Date: 6/15/2012
Citation: Rao, X., Yang, C., Ying, Y., Chao, K., Kim, M.S. 2012. Classification of Korla fragrant pears using NIR hyperspectral imaging analysis. Proceedings of SPIE. 8369:83690Y.

Interpretive Summary:

Technical Abstract: Korla fragrant pears are small oval pears characterized by light green skin, crisp texture, and a pleasant perfume for which they are named. Anatomically, the calyx of a fragrant pear may be either persistent or deciduous; the deciduous-calyx fruits are considered more desirable due to taste and texture attributes. Packing plants often target a maximum of 5% of the persistent-calyx type in packed cases of the fruit. Near-infrared hyperspectral imaging was investigated as a potential means for automated sorting of pears according to calyx type. Hyperspectral images spanning the 992-1681 nm region were acquired using an laboratory line-scan hyperspectral imaging system. Analysis of the hyperspectral images was performed to select wavebands useful for identifying and differentiating persistent-calyx and deciduous-calyx pears. Based on the selected wavebands, an image-processing algorithm demonstrated successful classification of 93.3% of 166 test-group pears into the two categories.