Publication detail

Approaches to Clustering of Microbial Colonies on Agar Plates

CICATKA, M. BURGET, R LANCOS, J

Original Title

Approaches to Clustering of Microbial Colonies on Agar Plates

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

Agar plates with cultivated microbes are frequently used in many laboratories. Many approaches to analysing images with agar plates have been developed and they aim to automate tasks such as colony counting and colony picking. Image processing is mostly used for detection and/or segmentation of microbes in the agar plates. More complex analysis such as grouping of microbial mixtures on the plates or retrieving additional information about the microbes is still for the most part unexplored. This article proposes three solutions for clustering colonies on agar plates based on their visual properties and suggests a suitable evaluation metric to this problem. The first solution naively clusters all pixels in the image based on its RGB values and serves as a baseline experiment. The second experiment utilizes clustering of manually extracted features calculated for each microbial colony detected separately. The third experiment clusters the features from the custom trained autoencoder used as a feature extractor.

Keywords

agar plates, microbial colonies, clustering

Authors

CICATKA, M.; BURGET, R; LANCOS, J

Released

25. 4. 2023

Publisher

Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií

Location

Brno

ISBN

ISBN 978-80-214-6153

Book

Proceedings I of the 29th Student EEICT 2023 (General Papers)

Pages count

5

URL

BibTex

@inproceedings{BUT184372,
  author="Michal {Čičatka} and Radim {Burget} and Jan {Láncoš}",
  title="Approaches to Clustering of Microbial Colonies on Agar Plates",
  booktitle="Proceedings I of the 29th Student EEICT 2023 (General Papers)",
  year="2023",
  pages="5",
  publisher="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  address="Brno",
  isbn="ISBN 978-80-214-6153",
  url="https://www.eeict.cz/download"
}