Original title: Analýza vývoje rostlin pomocí umělé inteligence
Authors: Hežel, Hugo ; Juránková, Markéta (referee) ; Bažout, David (advisor)
Document type: Bachelor's theses
Year: 2024
Language: slo
Publisher: Vysoké učení technické v Brně. Fakulta informačních technologií
Abstract: [slo] [eng]
Táto práca rozoberá problematiku monitorovania rastu rastlín, umelých neurónových sietí, konvolučných neurónových sietí a venuje takisto pozornosť ich zostaveniu. Predstavili sme návrh dvoch architektonicky odlišných modelov konvolučnej neurónovej siete pre rozpoznávanie vývoja rastliny. Tieto modely sme otestovali a porovnali, pričom model so zložitejšou architektúrou priniesol len o niečo lepšie výsledky, ako model s minimalistickou architektúrou. This paper discusses the issues of plant growth monitoring, artificial neural networks, convolutional neural networks and also pays attention to their construction. We presented the design of two architecturally different convolutional neural network models for plant growth recognition. We tested and compared these models, and the model with the more complex architecture yielded only slightly better results than the model with the minimalist architecture.
Keywords: artificial neural network; convolutional neural network; plant growth; plant growth monitoring; plants

Institution: Brno University of Technology (web)
Document availability information: Fulltext is available in the Brno University of Technology Digital Library.
Original record: https://hdl.handle.net/11012/246585

Permalink: http://www.nusl.cz/ntk/nusl-617147


The record appears in these collections:
Universities and colleges > Public universities > Brno University of Technology
Academic theses (ETDs) > Bachelor's theses