Next Article in Journal
Unsupervised Learning for Product Use Activity Recognition: An Exploratory Study of a “Chatty Device”
Previous Article in Journal
Recent Advances in Generation and Detection of Orbital Angular Momentum Optical Beams—A Review
Previous Article in Special Issue
Prediction of Fruity Aroma Intensity and Defect Presence in Virgin Olive Oil Using an Electronic Nose
Article

Classification Learning of Latent Bruise Damage to Apples Using Shortwave Infrared Hyperspectral Imaging

1
Eresearch Office, DVC—Research and Innovation, University of the Western Cape, Private Bag X17, Bellville 7535, South Africa
2
SARChI Postharvest Technology Research Laboratory, Faculty of AgrSciences, African Institute for Postharvest Technology, Stellenbosch University, Private Bag X1, Stellenbosch 7602, South Africa
3
Department of Electrical and Electronic Engineering, Stellenbosch University, Private Bag X1, Stellenbosch 7602, South Africa
4
UNESCO International Centre for Biotechnology, Nsukka 410001, Nigeria
*
Author to whom correspondence should be addressed.
Academic Editors: Paweł Pławiak, Tomislav Jemrić and Xiaoshuan Zhang
Sensors 2021, 21(15), 4990; https://doi.org/10.3390/s21154990
Received: 30 May 2021 / Revised: 29 June 2021 / Accepted: 1 July 2021 / Published: 22 July 2021
Bruise 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. View Full-Text
Keywords: machine learning; bruise detection; classification model; latent damage machine learning; bruise detection; classification model; latent damage
Show Figures

Figure 1

MDPI and ACS Style

Nturambirwe, J.F.I.; Perold, W.J.; Opara, U.L. Classification Learning of Latent Bruise Damage to Apples Using Shortwave Infrared Hyperspectral Imaging. Sensors 2021, 21, 4990. https://doi.org/10.3390/s21154990

AMA Style

Nturambirwe JFI, Perold WJ, Opara UL. Classification Learning of Latent Bruise Damage to Apples Using Shortwave Infrared Hyperspectral Imaging. Sensors. 2021; 21(15):4990. https://doi.org/10.3390/s21154990

Chicago/Turabian Style

Nturambirwe, Jean F.I., Willem J. Perold, and Umezuruike L. Opara 2021. "Classification Learning of Latent Bruise Damage to Apples Using Shortwave Infrared Hyperspectral Imaging" Sensors 21, no. 15: 4990. https://doi.org/10.3390/s21154990

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop