Computerized Classification Systemfor the Identification of Soil Microorganisms

Authors

Michał Kruk, Faculty of Applied Informatics & Mathematics, Warsaw University of Life Sciences, ul. Nowoursynowska 159, 02-776 Warsaw, PolandFollow
Ryszard Kozera, Faculty of Applied Informatics & Mathematics, Warsaw University of Life Sciences, ul. Nowoursynowska 159, 02-776 Warsaw, PolandFollow
Stanisław Osowski, Faculty of Electrical Engineering, Warsaw University of Technology, Pl. Politechniki 1, 00-661 Warsaw, Poland\\ Military University of Technology, Kaliskiego 2, 00-908 Warsaw, PolandFollow
Paweł Trzciǹski, Research Institute of Horticulture, ul. Pomologiczna 18, 96-100 Skierniewice, PolandFollow
Lidia Sas-Paszt, Research Institute of Horticulture, ul. Pomologiczna 18, 96-100 Skierniewice, PolandFollow
Beata Sumorok, Research Institute of Horticulture, ul. Pomologiczna 18, 96-100 Skierniewice, PolandFollow

Author Country (or Countries)

Poland

Abstract

This paper presents the method of soil microorganisms identification from the microscopic digital images. The proposed approach includes: segmentation of the image, feature generation, selection of the most important features and the final recognition stage applying five different solutions of classifiers. The paper presents and discusses the results concerning the recognition of several most popular soil microorganisms: Bacillus subtilis, Paenibacillus glucanolyticus, Rachnella aquatilis, Scoleobasidium sp., Trichoderma sp., Pseudomonas fluorescens, Bacillus atrophaeus, Azotobacter sp., Streptomyces sp. and other bacterias and fungi. The proposed system enables the recognition of the microorganisms with the accuracy close to 98%.

Digital Object Identifier (DOI)

http://dx.doi.org/10.18576/amis/100103

Recommended Citation

Kruk, Michał; Kozera, Ryszard; Osowski, Stanisław; Trzciǹski, Paweł; Sas-Paszt, Lidia; and Sumorok, Beata (2016) "Computerized Classification Systemfor the Identification of Soil Microorganisms," Applied Mathematics & Information Sciences: Vol. 10: Iss. 1, Article 3.
DOI: http://dx.doi.org/10.18576/amis/100103
Available at: https://digitalcommons.aaru.edu.jo/amis/vol10/iss1/3