Publication detail

Application of YOLOv7 neural network model for control of laboratory processes

KIAC, M. ŘÍHA, K. KRAJSA, O.

Original Title

Application of YOLOv7 neural network model for control of laboratory processes

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

Currently, the world is experiencing an ever-increasing boom in the use of artificial intelligence, especially deep learning. Deep learning and its applications are increasingly popular and used in many fields, such as industry, security systems, and even medicine. This work deals with the problem of detection and evaluation of the pipetting process. The entire system is based on the use of a camera, respectively the camera of a mobile device or tablet, which is conveniently positioned to capture the scene being captured. All image processing, object detection using the {YOLOv7 (You Only Look Once 7. version)} model and subsequent other operations are performed on a mobile device or tablet. The YOLOv7 neural network model was trained on our own prepared dataset. This training set was created specifically for the analysis of the pipetting process. The result of this work is a prepared annotated dataset and a trained YOLOv7 neural network model, which is aimed at detecting the entire pipette and the tip of this pipette in the image scene. The output of the work is also an implemented algorithm that can perform a complex analysis of the pipetting process using the trained YOLOv7 model. All materials used, dataset and scripts used in this work are available at https://github.com/KicoSVK/Application-of-YOLOv7-for-control-of-laboratory-processes.

Keywords

pipette; microplate; wells; laboratory processes; image processing; convolutional neural network; object detection

Authors

KIAC, M.; ŘÍHA, K.; KRAJSA, O.

Released

25. 4. 2023

Publisher

Brno University of Technology, Faculty of Electrical Engineering and Communication

Location

Brno

ISBN

978-80-214-6153-6

Book

Proceedings of the 29th Conference STUDENT EEICT 2023

Edition

1

ISBN

2788-1334

Periodical

Proceedings II of the Conference STUDENT EEICT

State

Czech Republic

Pages from

384

Pages to

388

Pages count

4

URL

https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_1.pdf

BibTex

@inproceedings{BUT184045,
  author="Martin {Kiac} and Kamil {Říha} and Ondřej {Krajsa}",
  title="Application of YOLOv7 neural network model for control of laboratory processes",
  booktitle="Proceedings of the 29th Conference STUDENT EEICT 2023",
  year="2023",
  series="1",
  journal="Proceedings II of the Conference STUDENT EEICT",
  pages="4",
  publisher="Brno University of Technology, Faculty of Electrical Engineering and Communication",
  address="Brno",
  isbn="978-80-214-6153-6",
  issn="2788-1334",
  url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_1.pdf"
}