Institutions | About Us | Help | Gaeilge
rian logo


Mark
Go Back
Hyperspectral Imaging for the Detection of Microbial Spoilage of Mushrooms
Gaston, Edurne; Frias, Jesus Maria; Cullen, Patrick; O’Donnell, Colm; Gowen, Aoife
Brown blotch, caused by pathogenic Pseudomonas tolaasii, is the most problematic bacterial disease in Agaricus bisporus mushrooms; it reduces their consumer appeal in the market place, thus generating important economical losses worldwide. The mushroom industry is in need of fast and accurate evaluation methodologies to ensure that only high quality produce reaches the market. Hyperspectral imaging (HSI) is a non-destructive technique that combines imaging and spectroscopy to obtain spatial and spectral information from an object. The aim of this study was to investigate the potential of Vis-NIR HSI to identify microbiological damage in mushrooms and to discriminate it from mechanical damage. Hyperspectral images of mushrooms subjected to i) no treatment, ii) microbiological spoilage and iii) mechanical damage were taken during storage and spectra representing each of the classes were selected. Partial least squares- discriminant analysis (PLS-DA) was carried out in two steps: i) discrimination between undamaged and damaged mushrooms and ii) discrimination between damage sources (i.e. microbiological or mechanical). The models were applied at a pixel level and a decision tree was used to classify mushrooms into one of the aforementioned classes. A correct classification of >95% was achieved. This was the first reported study to employ HSI for the detection of damage of bacterial origin in horticultural products. The industry could incorporate the knowledge gained in this study towards the development of a HSI sensor to detect and classify mushroom damage of microbial and mechanical origin, enabling the rapid and automated identification of mushrooms of reduced marketability.
Keyword(s): mushrooms; brown blotch; Pseudomonas tolaasii; mechanical damage; vis-NIR hyperspectral imaging; PLS-DA.; Agriculture; Food Microbiology
Publication Date:
2011
Type: Conference item
Peer-Reviewed: Unknown
Contributor(s): This research was funded by the Irish Government Department of Agriculture, Fisheries and Food under the Food Institutional Research Measure (FIRM).
Institution: Dublin Institute of Technology
Citation(s): Conference papers
Publisher(s): Dublin Institute of Technology
File Format(s): application/pdf
First Indexed: 2011-05-31 05:45:18 Last Updated: 2018-01-20 06:49:12