Optimal vision system design for characterization of apples using US/VIS/NIR spectroscopy data
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Optimal vision system design for characterization of apples using US/VIS/NIR spectroscopy data. / Sharifzadeh, Sara; Martinez Vega, Mabel Virginia; Clemmensen, Line H. ; Ersbøll, Bjarne K.
20th International Conference on Systems, Signals and Image Processing (IWSSIP), 2013. IEEE, 2013. p. 11-14.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Optimal vision system design for characterization of apples using US/VIS/NIR spectroscopy data
AU - Sharifzadeh, Sara
AU - Martinez Vega, Mabel Virginia
AU - Clemmensen, Line H.
AU - Ersbøll, Bjarne K.
N1 - Conference code: 20
PY - 2013
Y1 - 2013
N2 - Quality monitoring of the food items by spectroscopy provides information in a large number of wavelengths including highly correlated and redundant information. Although increasing the information, the increase in the number of wavelengths causes the vision set-up to be more complex and expensive. In this paper, three sparse regression methods; lasso, elastic-net and fused lasso are employed for estimation of the chemical and physical characteristics of one apple cultivar using their high dimensional spectroscopic measurements. The use of sparse regression reduces the number of required wavelengths for prediction and thus, simplifies the required vision set-up. It is shown that, considering a tradeoff between the number of selected bands and the corresponding validation performance during the training step can result in a significant reduction in the number of bands at a small price in the test performance. Furthermore, appropriate regression methods for different number of bands and spectrophotometer design are determined
AB - Quality monitoring of the food items by spectroscopy provides information in a large number of wavelengths including highly correlated and redundant information. Although increasing the information, the increase in the number of wavelengths causes the vision set-up to be more complex and expensive. In this paper, three sparse regression methods; lasso, elastic-net and fused lasso are employed for estimation of the chemical and physical characteristics of one apple cultivar using their high dimensional spectroscopic measurements. The use of sparse regression reduces the number of required wavelengths for prediction and thus, simplifies the required vision set-up. It is shown that, considering a tradeoff between the number of selected bands and the corresponding validation performance during the training step can result in a significant reduction in the number of bands at a small price in the test performance. Furthermore, appropriate regression methods for different number of bands and spectrophotometer design are determined
KW - Apples
KW - VIS/NIR
KW - sparse regression
KW - spectroscopy
KW - lasso
KW - elastic-net
U2 - 10.1109/IWSSIP.2013.6623437
DO - 10.1109/IWSSIP.2013.6623437
M3 - Article in proceedings
SN - 978-1-4799-0941-4
SP - 11
EP - 14
BT - 20th International Conference on Systems, Signals and Image Processing (IWSSIP), 2013
PB - IEEE
Y2 - 7 July 2013 through 9 July 2013
ER -
ID: 146201840