Hollowness in white radishes was detected by hyperspectral imaging. Three illumination patterns were used and compared. Important wavelengths were determined by the successive projections algorithm. PLS-DA and back propagation neural networks were used for classifying hollowness. Satisfactory classification accuracy was acquired using semi-transmittance mode.
NGLC 2004-2010.National Geological Library of China All Rights Reserved.
Add:29 Xueyuan Rd,Haidian District,Beijing,PRC. Mail Add: 8324 mailbox 100083
For exchange or info please contact us via email.