We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Innovative infrastructure to access Brazilian fungal diversity using deep learning.
- Authors
Chaves, Thiago; Santos Xavier, Joicymara; Gonçalves dos Santos, Alfeu; Martins-Cunha, Kelmer; Karstedt, Fernanda; Kossmann, Thiago; Sourell, Susanne; Leopoldo, Eloisa; Fortuna Ferreira, Miriam Nathalie; Farias, Roger; Titton, Mahatmã; Alves-Silva, Genivaldo; Bittencourt, Felipe; Bortolini, Dener; Gumboski, Emerson L.; von Wangenheim, Aldo; Góes-Neto, Aristóteles; Drechsler-Santos, Elisandro Ricardo
- 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.
- Subjects
IMAGE recognition (Computer vision); COMPUTER vision; DATABASES; CONVOLUTIONAL neural networks; FUNGI classification
- Publication
PeerJ, 2024, p1
- ISSN
2167-8359
- Publication type
Article
- DOI
10.7717/peerj.17686