Classification of Fruit Flies by Gender in Images Using Smartphones and the YOLOv4-Tiny Neural Network

Mikhail A. Genaev, Evgenii G. Komyshev, Olga D. Shishkina, Natalya V. Adonyeva, Evgenia K. Karpova, Nataly E. Gruntenko, Lyudmila P. Zakharenko, Vasily S. Koval and Dmitry A. Afonnikov
Additional contact information
Mikhail A. Genaev: Mathematical Center in Akademgorodok, 630090 Novosibirsk, Russia
Evgenii G. Komyshev: Mathematical Center in Akademgorodok, 630090 Novosibirsk, Russia
Olga D. Shishkina: Institute of Cytology and Genetics, Siberian Branch of the Russian Academy of Sciences, 630090 Novosibirsk, Russia
Natalya V. Adonyeva: Institute of Cytology and Genetics, Siberian Branch of the Russian Academy of Sciences, 630090 Novosibirsk, Russia
Evgenia K. Karpova: Institute of Cytology and Genetics, Siberian Branch of the Russian Academy of Sciences, 630090 Novosibirsk, Russia
Nataly E. Gruntenko: Institute of Cytology and Genetics, Siberian Branch of the Russian Academy of Sciences, 630090 Novosibirsk, Russia
Lyudmila P. Zakharenko: Institute of Cytology and Genetics, Siberian Branch of the Russian Academy of Sciences, 630090 Novosibirsk, Russia
Vasily S. Koval: Institute of Cytology and Genetics, Siberian Branch of the Russian Academy of Sciences, 630090 Novosibirsk, Russia
Dmitry A. Afonnikov: Mathematical Center in Akademgorodok, 630090 Novosibirsk, Russia

Mathematics, 2022, vol. 10, issue 3, 1-19

Abstract: The fruit fly Drosophila melanogaster is a classic research object in genetics and systems biology. In the genetic analysis of flies, a routine task is to determine the offspring size and gender ratio in their populations. Currently, these estimates are made manually, which is a very time-consuming process. The counting and gender determination of flies can be automated by using image analysis with deep learning neural networks on mobile devices. We proposed an algorithm based on the YOLOv4-tiny network to identify Drosophila flies and determine their gender based on the protocol of taking pictures of insects on a white sheet of paper with a cell phone camera. Three strategies with different types of augmentation were used to train the network. The best performance ( F 1 = 0.838) was achieved using synthetic images with mosaic generation. Females gender determination is worse than that one of males. Among the factors that most strongly influencing the accuracy of fly gender recognition, the fly’s position on the paper was the most important. Increased light intensity and higher quality of the device cameras have a positive effect on the recognition accuracy. We implement our method in the FlyCounter Android app for mobile devices, which performs all the image processing steps using the device processors only. The time that the YOLOv4-tiny algorithm takes to process one image is less than 4 s.

Keywords: Drosophila melanogaster; gender; image analysis; deep learning; object detection; mobile device; Android app (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/3/295/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/3/295/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2022:i:3:p:295-:d:727846

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().