Segmentation of hyperspectral images for the detection of rotten mandarins
Derechos de accesoopenAccess
MetadataShow full item record
AuthorGomez-Sanchis, J.; Camps-Valls, G.; Moltó, Enrique; Gomez-Chova, L.; Aleixos, N.; Blasco, José
Cita bibliográficaGomez-Sanchis, J., Camps-Valls, G., Moltó, E., Gomez-Chova, L., Aleixos, N., Blasco, J. (2008). Segmentation of hyperspectral images for the detection of rotten mandarins. Image Analysis and Recognition, Proceedings, 5112, 1071-1080.
The detection of rotten citrus in packing lines is carried out manually under ultraviolet illumination, which is dangerous for workers. Light emitted by the rotten region of the fruit due to the ultraviolet-induced fluorescence is used by the operator to detect the damages. This procedure is required because the low contrast between the damaged and sound skin under visible illumination difficult their detection. We study a set of techniques aimed to detect rottenness in citrus using visible and near infrared lighting trough an hyperspectral imaging system. Methods for selecting a proper set of wavelengths are investigated such as correlation analysis, mutual information, stepwise or genetic algorithms. The image segmentation relies on the combination of band selection techniques and pixel classification methods such as classification and regression trees and linear discriminant analysis.