Title:	Fungi Recognition: A Practical Use Case
Authors:	Šulc, Milan Picek, Lukáš Matas, Jiří Jeppesen, Thomas Heilmann-Clausen, Jacob
Citation:	ŠULC, M. PICEK, L. MATAS, J. JEPPESEN, T. HEILMANN-CLAUSEN, J.Fungi Recognition: A Practical Use Case. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV). Red Hook, NY: IEEE, 2020. s. 2305-2313. ISBN 978-1-72816-553-0, ISSN 2472-6737.
Issue Date:	2020
Publisher:	IEEE
Document type:	konferenční příspěvek conferenceObject
URI:	2-s2.0-85085504154 http://hdl.handle.net/11025/42937
ISBN:	978-1-72816-553-0
ISSN:	2472-6737
Keywords in different language:	visual recognition, fungi, web- and mobile interfaces
Abstract in different language:	The paper presents a system for visual recognition of1394 fungi species based on deep convolutional neuralnetworks and its deployment in a citizen-science project.The system allows users to automatically identify observedspecimens, while providing valuable data to biologists andcomputer vision researchers. The underlying classifica-tion method scored first in the FGVCx Fungi ClassificationKaggle competition organized in connection with the Fine-Grained Visual Categorization (FGVC) workshop at CVPR2018. We describe our winning submission and evaluate alltechnicalities that increased the recognition scores, and dis-cuss the issues related to deployment of the system via theweb- and mobile- interfaces.
Rights:	© IEEE
Appears in Collections:	Postprinty / Postprints (KKY) Postprinty / Postprints (NTIS) OBD

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.