Comparison of ROC Feature Selection Method for the Detection of Decay in Citrus Fruit Using Hyperspectral Images
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 losse...
| Main Authors: | , , , , , |
|---|---|
| Format: | Artículo |
| Language: | Inglés |
| Published: |
2017
|
| Online Access: | http://hdl.handle.net/20.500.11939/5538 |
| _version_ | 1855491942077431808 |
|---|---|
| author | Lorente, Delia Blasco, José Serrano, A. J. Soria-Olivas, Emilio Aleixos, Nuria Gómez-Sanchís, Juan |
| author_browse | Aleixos, Nuria Blasco, José Gómez-Sanchís, Juan Lorente, Delia Serrano, A. J. Soria-Olivas, Emilio |
| author_facet | Lorente, Delia Blasco, José Serrano, A. J. Soria-Olivas, Emilio Aleixos, Nuria Gómez-Sanchís, Juan |
| author_sort | Lorente, Delia |
| collection | ReDivia |
| description | 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. |
| format | Artículo |
| id | ReDivia5538 |
| institution | Instituto Valenciano de Investigaciones Agrarias (IVIA) |
| language | Inglés |
| publishDate | 2017 |
| publishDateRange | 2017 |
| publishDateSort | 2017 |
| record_format | dspace |
| spelling | ReDivia55382025-04-25T14:43:14Z Comparison of ROC Feature Selection Method for the Detection of Decay in Citrus Fruit Using Hyperspectral Images Lorente, Delia Blasco, José Serrano, A. J. Soria-Olivas, Emilio Aleixos, Nuria Gómez-Sanchís, Juan 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. 2017-06-01T10:12:32Z 2017-06-01T10:12:32Z 2013 DEC 2013 article acceptedVersion Lorente, D., Blasco, J., Serrano, A. J., Soria-Olivas, E., Aleixos, N., Gomez-Sanchis, J. (2013). Comparison of ROC Feature Selection Method for the Detection of Decay in Citrus Fruit Using Hyperspectral Images. Food and Bioprocess Technology, 6(12), 3613-3619. 1935-5130; 1935-5149 http://hdl.handle.net/20.500.11939/5538 10.1007/s11947-012-0951-1 en openAccess Impreso |
| spellingShingle | Lorente, Delia Blasco, José Serrano, A. J. Soria-Olivas, Emilio Aleixos, Nuria Gómez-Sanchís, Juan Comparison of ROC Feature Selection Method for the Detection of Decay in Citrus Fruit Using Hyperspectral Images |
| title | Comparison of ROC Feature Selection Method for the Detection of Decay in Citrus Fruit Using Hyperspectral Images |
| title_full | Comparison of ROC Feature Selection Method for the Detection of Decay in Citrus Fruit Using Hyperspectral Images |
| title_fullStr | Comparison of ROC Feature Selection Method for the Detection of Decay in Citrus Fruit Using Hyperspectral Images |
| title_full_unstemmed | Comparison of ROC Feature Selection Method for the Detection of Decay in Citrus Fruit Using Hyperspectral Images |
| title_short | Comparison of ROC Feature Selection Method for the Detection of Decay in Citrus Fruit Using Hyperspectral Images |
| title_sort | comparison of roc feature selection method for the detection of decay in citrus fruit using hyperspectral images |
| url | http://hdl.handle.net/20.500.11939/5538 |
| work_keys_str_mv | AT lorentedelia comparisonofrocfeatureselectionmethodforthedetectionofdecayincitrusfruitusinghyperspectralimages AT blascojose comparisonofrocfeatureselectionmethodforthedetectionofdecayincitrusfruitusinghyperspectralimages AT serranoaj comparisonofrocfeatureselectionmethodforthedetectionofdecayincitrusfruitusinghyperspectralimages AT soriaolivasemilio comparisonofrocfeatureselectionmethodforthedetectionofdecayincitrusfruitusinghyperspectralimages AT aleixosnuria comparisonofrocfeatureselectionmethodforthedetectionofdecayincitrusfruitusinghyperspectralimages AT gomezsanchisjuan comparisonofrocfeatureselectionmethodforthedetectionofdecayincitrusfruitusinghyperspectralimages |