prikaz prve stranice dokumenta Raspoznavanje bolesti rajčice uporabom prijenosnog dubokog strojnog učenja na temelju slike razvijenim modulom IncMB
  Download
PDF 2.91 MB
master's thesis
Raspoznavanje bolesti rajčice uporabom prijenosnog dubokog strojnog učenja na temelju slike razvijenim modulom IncMB
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2022. urn:nbn:hr:200:484294
Radočaj, Petra
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Programming Languages and Systems

Institutional repository: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek

Cite this document

Radočaj, P. (2022). Raspoznavanje bolesti rajčice uporabom prijenosnog dubokog strojnog učenja na temelju slike razvijenim modulom IncMB (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:484294

Radočaj, Petra. "Raspoznavanje bolesti rajčice uporabom prijenosnog dubokog strojnog učenja na temelju slike razvijenim modulom IncMB." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2022. https://urn.nsk.hr/urn:nbn:hr:200:484294

Radočaj, Petra. "Raspoznavanje bolesti rajčice uporabom prijenosnog dubokog strojnog učenja na temelju slike razvijenim modulom IncMB." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2022. https://urn.nsk.hr/urn:nbn:hr:200:484294

Radočaj, P. (2022). 'Raspoznavanje bolesti rajčice uporabom prijenosnog dubokog strojnog učenja na temelju slike razvijenim modulom IncMB', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 09 May 2024, https://urn.nsk.hr/urn:nbn:hr:200:484294

Radočaj P. Raspoznavanje bolesti rajčice uporabom prijenosnog dubokog strojnog učenja na temelju slike razvijenim modulom IncMB [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2022 [cited 2024 May 09] Available at: https://urn.nsk.hr/urn:nbn:hr:200:484294

P. Radočaj, "Raspoznavanje bolesti rajčice uporabom prijenosnog dubokog strojnog učenja na temelju slike razvijenim modulom IncMB", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:200:484294

Metadata
TitleRaspoznavanje bolesti rajčice uporabom prijenosnog dubokog strojnog učenja na temelju slike razvijenim modulom IncMB
Title (english)Recognition of tomato diseases from images by using transfer deep machine learning and developed IncMB module
AuthorPetra Radočaj
MentorGoran Martinović (mentor)
Committee memberGoran Martinović (predsjednik povjerenstva)
Committee memberKrešimir Nenadić (član povjerenstva)
Committee memberIvan Aleksi (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Programming Languages and Systems)
Osijek
Defense date and country2022-07-10, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
U teorijskom dijelu rada prikazane su bolesti rajčice, prateći simptomi i načini dijagnosticiranja bolesti. Opisani su modeli za raspoznavanje bolesti lista rajčice temeljeni na prijenosnom dubokom strojnom učenju. Problem klasifikacije pomoću konvolucijskih neuronskih mreža unaprjeđen je razvojem IncMB modula. Znanje o načinu na koji algoritmi dubokog strojnog učenja izdvajaju značajke povećalo bi točnost detekcije bolesti, osiguralo bržu dijagnostiku i odabir pravilnog tretmana. U eksperimentalnom dijelu rada se na mrežnim arhitekturama InceptionResNetV2, InceptionV3, MobileNetV2 i DenseNet201 provela klasifikacija bolesti lista rajčice i to implementacijom pojedine mreže, njezine inačice s IncMB modulom i inačice s metodom potpornih vektora. Svi modeli su trenirani i validirani na javno dostupnom skupu podataka u kojem su bolesne jedinke rajčice određene u šest klasa. Najbolje rezultate ostvarila je InceptionV3 mreža koja sarži IncMB modul čija je točnost naveća.
Abstract (english)
The theoretical part of the thesis describes tomato diseases, symptoms, and diagnostic methods. Models for recognizing tomato leaf disease based on transfer deep machine learning are implemented. The classification problem using convolutional neural networks has been improved by the development of IncMB module. Knowledge of how deep machine learning algorithms extract features would contribute to the accuracy of disease detection, faster diagnosis, and selection of the proper treatment. In the experimental part of the thesis, tomato leaf disease classification was performed on InceptionResNetV2, InceptionV3, MobileNetV2, and DenseNet201 network architectures by implementing an individual network, its version with IncMB module and version with support vector machine. All models were trained and validated on a public dataset containing diseased tomato individuals divided into six classes. The best results were achieved by the InceptionV3 network, which contains an IncMB module with an accuracy of 97.78%.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:484294
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 on2022-09-07 12:24:26