Classification learning of latent bruise damage to apples using shortwave infrared hyperspectral imaging

Simple item page
dc.contributor.authorNturambirwe, Jean Frederic Isingizween_ZA
dc.contributor.authorPerold, Willem Jacobusen_ZA
dc.contributor.authorOpara, Umezuruike Linusen_ZA
dc.date.accessioned2023-03-31T06:37:13Z
dc.date.available2023-03-31T06:37:13Z
dc.date.issued2021-07-22
dc.descriptionCITATION: Nturambirwe, J. F. I., Perold, W. J. & Opara, U. L. 2021. Classification learning of latent bruise damage to apples using shortwave infrared hyperspectral imaging. Sensors, 21(15):4990, doi:10.3390/s21154990.en_ZA
dc.descriptionThe original publication is available at https://www.mdpi.comen_ZA
dc.description.abstractBruise damage is a very commonly occurring defect in apple fruit which facilitates disease occurrence and spread, leads to fruit deterioration and can greatly contribute to postharvest loss. The detection of bruises at their earliest stage of development can be advantageous for screening purposes. An experiment to induce soft bruises in Golden Delicious apples was conducted by applying impact energy at different levels, which allowed to investigate the detectability of bruises at their latent stage. The existence of bruises that were rather invisible to the naked eye and to a digital camera was proven by reconstruction of hyperspectral images of bruised apples, based on effective wavelengths and data dimensionality reduced hyperspectrograms. Machine learning classifiers, namely ensemble subspace discriminant (ESD), k-nearest neighbors (KNN), support vector machine (SVM) and linear discriminant analysis (LDA) were used to build models for detecting bruises at their latent stage, to study the influence of time after bruise occurrence on detection performance and to model quantitative aspects of bruises (severity), spanning from latent to visible bruises. Over all classifiers, detection models had a higher performance than quantitative ones. Given its highest speed in prediction and high classification performance, SVM was rated most recommendable for detection tasks. However, ESD models had the highest classification accuracy in quantitative (>85%) models and were found to be relatively better suited for such a multiple category classification problem than the rest.en_ZA
dc.description.urihttps://www.mdpi.com/1424-8220/21/15/4990
dc.description.versionPublisher's versionen_ZA
dc.format.extent17 pages : illustrationsen_ZA
dc.identifier.citationNturambirwe, J. F. I., Perold, W. J. & Opara, U. L. 2021. Classification learning of latent bruise damage to apples using shortwave infrared hyperspectral imaging. Sensors, 21(15):4990, doi:10.3390/s21154990.en_ZA
dc.identifier.issn1424-8220 (online)
dc.identifier.otherdoi:10.3390/s21154990
dc.identifier.urihttp://hdl.handle.net/10019.1/126743
dc.language.isoen_ZAen_ZA
dc.publisherMDPIen_ZA
dc.rights.holderAuthors retain copyrighten_ZA
dc.subjectApples -- Postharvest technologyen_ZA
dc.subjectApples -- Defects -- Detectionen_ZA
dc.subjectApples -- Wounds and injuries -- Defects -- Imagingen_ZA
dc.subjectApples -- Classificationen_ZA
dc.subjectHyperspectral imagingen_ZA
dc.titleClassification learning of latent bruise damage to apples using shortwave infrared hyperspectral imagingen_ZA
dc.typeArticleen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
nturambirwe_classification_2021.pdf
Size:
4.63 MB
Format:
Adobe Portable Document Format
Description:
Download article
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Research Articles (Horticulture)
Research Articles (Electrical and Electronic Engineering)