Identification of bacteria species by using morphological and textural
properties of bacterial colonies diffraction patterns
A. Suchwalko, I. Buzalewicz, H. Podbielska
Institute of Biomedical Engineering and Instrumentation, Wroclaw University of Technology,
ul. Wybrzeze Wyspianskiego 27, 50-370 Wroclaw, Poland;
ABSTRACT
In our previous study we have shown that identification of bacteria species with the use of Fresnel diffraction patterns is
possible with high accuracy and at low cost. Fresnel diffraction patterns were recorded with the optical system with
converging spherical wave illumination. Obtained experimental results have shown that colonies of specific bacteria
species generate unique diffraction signatures. Features used for building classification models and thus for identification
were simply mean value and standard deviation calculated of pixel intensities within regions of interest called rings. This
work presents new, interpretable features denoting morphological and textural properties of the Fresnel diffraction
patterns and their verification with the use of the statistical analysis workflow specially developed for bacteria species
identification. As data set of bacteria species diffraction patterns it is very important to find features that differentiate
species in the best manner. This task includes two steps. The first is finding and extracting new, interpretable features
that can potentially be better for bacteria species differentiation than the ones used before. While the second one is
deciding which of them are the best for identification purposes. The new features are calculated basing on normalized
diffraction patterns and central statistical moments. For the verification the analysis workflow based on ANOVA for
feature selection, LDA, QDA and SVM models for classification and identification and CV, sensitivity and specificity
for performance assessment of the identification process, are applied. Additionally, the Fisher divergence method also
known as signal to noise ratio (SNR) for feature selection was exploited.
Keywords: bacteria species identification, statistical analysis, Fresnel diffraction patterns, image processing,
classification models
1. INTRODUCTION
Identification of bacterial species is the procedure carried out every day in all of microbiological laboratories around the
world. There are many techniques for identifying the bacterial species with high reliability but most of them are
expensive or the tests are time consuming. The optical methods for bacterial species identification can be reliable, fast
and not expensive. Moreover the optical investigation of biological samples has non-contact and non-destructive
character, therefore in case of ambiguous results the sample can be verified by others methods, what is significant
advantage in comparison with biochemical and molecular methods.
The studies conducted so far have led to the development of the initial method, which allows identification of the
bacterial species with high accuracy (over 98%)
1
,
2
. As the data set is smaller than the target data set, slight deterioration
of the results after application of the initial method to large data is expected. Therefore our further concern is to improve
the initial method, so it will be suitable for large data sets.
The target data set consists of many classes (hundreds of existing and yet unknown bacteria species), relatively few
observations (about 100 diffraction patterns of each bacteria species) and many potential features differentiating classes
(many morphological and textural properties of the bacterial colonies diffraction patterns). The number of bacteria
species can be large. Number of Fresnel diffraction patterns is limited. More patterns will lead to better classification
models but the number must be fixed at some point. Therefore, this work concentrates on the morphological and textural
properties of bacterial colonies diffraction patterns. Our goal is to propose new and easily interpretable features based on
the morphological and textural properties of bacterial colonies diffraction patterns and verify bacterial species
differentiation capabilities with the use of previously developed statistical analysis workflow with added SNR separation
measure.
Videometrics, Range Imaging, and Applications XII; and Automated Visual Inspection, edited by Fabio Remondino,
Mark R. Shortis, Jürgen Beyerer, Fernando Puente León, Proc. of SPIE Vol. 8791, 87911M
© 2013 SPIE · CCC code: 0277-786X/13/$18 · doi: 10.1117/12.2020337
Proc. of SPIE Vol. 8791 87911M-1
Downloaded From: http://proceedings.spiedigitallibrary.org/ on 05/24/2013 Terms of Use: http://spiedl.org/terms