Comparison of ROC Feature Selection Method for the Detection of Decay in Citrus Fruit Using Hyperspectral Images
- 681 Downloads
Hyperspectral imaging systems allow to detect the initial stages of decay caused by fungi in citrus fruit automatically, instead of doing it manually under dangerous ultraviolet illumination, thus preventing the fungal infestation of other sound fruit and, consequently, the enormous economical losses generated. However, these systems present the disadvantage of generating a huge amount of data, which is necessary to select for achieving some result useful for the sector. There are numerous feature selection methods to reduce dimensionality of hyperspectral images. This work compares a feature selection method using the area under the receiver operating characteristic (ROC) curve with other common feature selection techniques, in order to select an optimal set of wavelengths effective in the detection of decay in a citrus fruit using hyperspectral images. This comparative study is done using images of mandarins with the pixels labelled in five different classes: two types of healthy skin, two types of decay and scars, ensuring that the ROC technique generally provides better results than the other methods.
KeywordsComputer vision Citrus fruit Decay Non-destructive inspection Hyperspectral imaging ROC curve Feature selection
This work has been partially funded by the Universitat de València through project UV-INV-AE11-41271, by the Instituto Nacional de Investigación y Tecnología Agraria y Alimentaria de España (INIA) through research project RTA2009-00118-C02-01 and by the Ministerio de Ciencia e Innovación de España (MICINN) through research project DPI2010-19457, both projects with the support of European FEDER funds.
- Bonnlander, B.V., & Weigend, A.S. (1994). Selecting input variables using mutual information and nonparametric density estimation. In: Proceedings of the 1994 International Symposium on Artificial Neural Networks (ISANN’94), Tainan, Taiwan, pp. 42–50.Google Scholar
- Eckert, J., & Eaks, I. (1989). Postharvest disorders and diseases of citrus. In W. Reuther, E. C. Calavan, & G. E. Carman (Eds.), The citrus industry. Berkeley: University California Press.Google Scholar
- Kullback, S. (1987). The Kullback–Leibler distance. The American Statistician, 41, 340–341.Google Scholar
- Kurita, M., Kondo, N., Shimizu, H., Ling, P., Falzea, P. D., Shiigi, T., et al. (2009). A double image acquisition system with visible and UV LEDs for citrus fruit. Journal of Robotics and Mechatronics, 21(4), 533–540.Google Scholar
- Lorente, D., Aleixos, N., Gómez-Sanchis, J., Cubero, S., & Blasco, J. (2011). Selection of optimal wavelength features for decay detection in citrus fruit using the ROC curve and neural networks. Food and Bioprocess Technology. doi: 10.1007/s11947-011-0737-x.
- Ouardighi, A., Akadi, A., Aboutajdine, D. (2007). Feature selection on supervised classification using Wilks lambda statistic. In: International Symposium on Computational Intelligence and Intelligent Informatics ISCIII07, 1, pp. 51–55.Google Scholar
- Rifkin, R., & Klautau, A. (2004). In defense of one-vs-all classification. Journal of Machine Learning Research, 5, 101–141.Google Scholar
- Serrano, A.J., Soria, E., Martín, J.D., Magdalena, R. Gómez, J. (2010). Feature selection using ROC curves on classification problems. In: International Joint Conference on Neural Networks, IJCNN 2010. 28th–30th July 2010. Barcelona, Spain. Proceedings, pp. 1980–1985.Google Scholar
- Zude, M. (Ed.). (2008). Optical monitoring of fresh and processed agricultural crops. Boca Raton: CRC.Google Scholar