A method for comparison of growth media in objective identification of Penicillium based on multi-spectral imaging



AbstractWe consider the problems of using excessive growth media for
identification and performing objective identification of fungi at
the species level. We propose a method for choosing the subset of
growth media, which provides the best discrimination between
several fungal species. Furthermore, we propose the use of
multi-spectral imaging as a means of objective identification.
Three species of the fungal genus Penicillium are subject
to classification. To obtain an objective classification we use
multi-spectral images. Previously, RGB images have proven useful
for the purpose. We use multi-spectral bands as they provide
additional information about the chemistry of the fungal colonies.
In this study three media [Czapek yeast extract agar (CYA),
oatmeal agar (OAT), and yeast extract sucrose agar (YES)] have
been compared on their ability to discriminate between the three
species. We propose a statistical method to test which medium or
combination of media gives the best discrimination.

Statistical tests indicate that YES combined with CYA is the best
choice of media in this case. However, for the objective
identification one medium is sufficient to discriminate between
the species. Statistical tests show that there are significant
differences between the species on all individual media, and that
these differences are largest on YES. The objective identification
has been performed solely by means of digital image analysis. The
features obtained from the image analysis merely correspond to
macro-morphological features. The species have been classified
using only 3-4 of the spectral bands with a 100% correct
classification rate using both leave-one-out cross-validation and
test set validation.
KeywordsChoice of growth media, Filamentous fungi, Macro-morphology, Multi-spectral images, Objective identification, Penicillium
TypeJournal paper [With referee]
JournalJournal of Microbiological Methods
Year2007    Month January    Vol. 69    pp. 249-255
Electronic version(s)[pdf]
BibTeX data [bibtex]
IMM Group(s)Image Analysis & Computer Graphics