online read us now
Paper details
Number 3 - September 2020
Volume 30 - 2020
Recognition of species and genera of bacteria by means of the product of weights of the classifiers
Anna Plichta
Abstract
In microbiology, computer methods are applied in the analysis and recognition of laboratory-acquired microscopic images
concerning, for example, bacterial cells or other microorganisms. Proper recognition of the species and genera of bacteria is
a key stage in the microbiological diagnostics process, because it allows a quick start of the appropriate therapy. The original
method proposed in the paper concerns the automatic recognition of selected species and genera of bacteria presented in
digital images. The classification was made on the basis of the analysis of the physical characteristics of bacterial cells
using the product of classifier confidence weights. The end result of the classification process is the classification list,
sorted in descending order according to the weights of the classifiers. In addition to the correct classification, a list of other
possible results of the analysis is obtained. The method thus allows not only the classification, but also an analysis of the
confidence level of the selection made. The proposed method can be used to recognize not only bacterial cells, but also other
microorganisms, for example, fungi that exhibit similar morphological characteristics. In addition, the use of the method
does not require the application of specialized computer equipment, which widens the scope of applications regardless of
the laboratory IT infrastructure, not only in microbiological diagnostics, but also in other diagnostic laboratories.
Keywords
pattern recognition, recognition of bacterial cells, classifiers, product of weights of the classifiers