prikaz prve stranice dokumenta Prepoznavanje bolesti vinove loze sa slika
  Download
PDF 1.65 MB
master's thesis
Prepoznavanje bolesti vinove loze sa slika
2020. urn:nbn:hr:200:320379
Markota, Krešimir
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Computer Engineering and Automation
Chair of Automation and Robotics

Cite this document

Markota, K. (2020). Prepoznavanje bolesti vinove loze sa slika (Master's thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:320379

Markota, Krešimir. "Prepoznavanje bolesti vinove loze sa slika." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. https://urn.nsk.hr/urn:nbn:hr:200:320379

Markota, Krešimir. "Prepoznavanje bolesti vinove loze sa slika." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. https://urn.nsk.hr/urn:nbn:hr:200:320379

Markota, K. (2020). 'Prepoznavanje bolesti vinove loze sa slika', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 02 July 2022, https://urn.nsk.hr/urn:nbn:hr:200:320379

Markota K. Prepoznavanje bolesti vinove loze sa slika [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2020 [cited 2022 July 02] Available at: https://urn.nsk.hr/urn:nbn:hr:200:320379

K. Markota, "Prepoznavanje bolesti vinove loze sa slika", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:200:320379

Please login to the repository to save this object to your list.
Metadata
TitlePrepoznavanje bolesti vinove loze sa slika
Title (english)Identifying grapevine diseases from images
AuthorKrešimir Markota
MentorEmmanuel Karlo Nyarko (mentor)
Committee memberEmmanuel Karlo Nyarko (predsjednik povjerenstva)
Committee memberDamir Filko (član povjerenstva)
Committee memberPetra Đurović (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Computer Engineering and Automation)
(Chair of Automation and Robotics)
Osijek
Defense date and country2020-10-09, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
Za konkurentnost na tržištu u proizvodnji vina potrebno je imati najkvalitetnije moguće sirovine grožđa kako bi se proizvelo što kvalitetnije vino. Vinari u modernom dobu izdvajaju velika novčana sredstva za obranu vinograda od bolesti vinove loze. Utrošena novčana sredstva se značajnije smanjuju ranim otkrivanjem bolesti vinove loze. Zadatak ovog diplomskog rada bio je istražiti i izraditi sustav za prepoznavanje bolesti vinove loze sa slika, a pri tome su korištene metode neuronskih mreža. Prije samog treniranja neuronskih mreža, potrebno je prikupiti i predobraditi podatke. Programska podrška za ovakav sustav napisana je u programskom jeziku Python. Nadalje, dobiveni rezultati treniranih modela su uspoređeni te su odabrani najbolji kojima su se vršila testiranja. Neuronske mreže su se pokazale kao vrlo dobra metoda za uspješno prepoznavanje bolesti vinove loze.
Abstract (english)
In order to be competitive on the market, in wine production it is necessary to have grapes of the highest possible quality in order to produce wine of the highest quality. Winemakers in the modern age give large sums of money to defend vineyards from diseases. By early detection of diseases, the need for spending funds on protection is significantly reduced. The aim of this study was to investigate and develop a system for detection of grape vine diseases from images, using neural network methods. Before training of neural networks, it is necessary to collect and pre-process the data. Software for such system is written in the Python programming language. Furthermore, the obtained results of the trained models were compared and the best ones were selected and tested. Neural networks have proven to be a very good method for successfully recognizing grape vine diseases.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:320379
Study programmeTitle: Graduate University Study Programme in Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2020-12-04 08:03:55