1. Innovative infrastructure to access Brazilian fungal diversity using deep learning.
- Author
-
Chaves T, Santos Xavier J, Gonçalves Dos Santos A, Martins-Cunha K, Karstedt F, Kossmann T, Sourell S, Leopoldo E, Fortuna Ferreira MN, Farias R, Titton M, Alves-Silva G, Bittencourt F, Bortolini D, Gumboski EL, von Wangenheim A, Góes-Neto A, and Drechsler-Santos ER
- Subjects
- Brazil, Biodiversity, Neural Networks, Computer, Databases, Factual, Deep Learning, Fungi classification, Fungi isolation & purification
- Abstract
In the present investigation, we employ a novel and meticulously structured database assembled by experts, encompassing macrofungi field-collected in Brazil, featuring upwards of 13,894 photographs representing 505 distinct species. The purpose of utilizing this database is twofold: firstly, to furnish training and validation for convolutional neural networks (CNNs) with the capacity for autonomous identification of macrofungal species; secondly, to develop a sophisticated mobile application replete with an advanced user interface. This interface is specifically crafted to acquire images, and, utilizing the image recognition capabilities afforded by the trained CNN, proffer potential identifications for the macrofungal species depicted therein. Such technological advancements democratize access to the Brazilian Funga, thereby enhancing public engagement and knowledge dissemination, and also facilitating contributions from the populace to the expanding body of knowledge concerning the conservation of macrofungal species of Brazil., Competing Interests: Aristóteles Góes-Neto is an Academic Editor for PeerJ., (© 2024 Chaves et al.)
- Published
- 2024
- Full Text
- View/download PDF