prikaz prve stranice dokumenta A comparison of accuracy of image recognition apps for identification of segetal and ruderal flora
  Download
PDF 1.5 MB
master's thesis
A comparison of accuracy of image recognition apps for identification of segetal and ruderal flora
2023. urn:nbn:hr:151:093514
Bilić, Davor
Josip Juraj Strossmayer University of Osijek
Faculty of Agrobiotechnical Sciences Osijek
Department of Phytomedicine

Cite this document

Bilić, D. (2023). A comparison of accuracy of image recognition apps for identification of segetal and ruderal flora (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Agrobiotechnical Sciences Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:151:093514

Bilić, Davor. "A comparison of accuracy of image recognition apps for identification of segetal and ruderal flora." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Agrobiotechnical Sciences Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:151:093514

Bilić, Davor. "A comparison of accuracy of image recognition apps for identification of segetal and ruderal flora." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Agrobiotechnical Sciences Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:151:093514

Bilić, D. (2023). 'A comparison of accuracy of image recognition apps for identification of segetal and ruderal flora', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Agrobiotechnical Sciences Osijek, accessed 02 April 2025, https://urn.nsk.hr/urn:nbn:hr:151:093514

Bilić D. A comparison of accuracy of image recognition apps for identification of segetal and ruderal flora [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Agrobiotechnical Sciences Osijek; 2023 [cited 2025 April 02] Available at: https://urn.nsk.hr/urn:nbn:hr:151:093514

D. Bilić, "A comparison of accuracy of image recognition apps for identification of segetal and ruderal flora", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Agrobiotechnical Sciences Osijek, Osijek, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:151:093514

Please login to the repository to save this object to your list.
Metadata
TitleA comparison of accuracy of image recognition apps for identification of segetal and ruderal flora
Title (croatian)Usporedba točnosti aplikacija za prepoznavanje slika za identifikaciju segetalne i ruderalne flore
AuthorDavor Bilić
MentorMarija Ravlić (mentor)
Committee memberVlatka Rozman (predsjednik povjerenstva)
Committee memberMonika Marković (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Agrobiotechnical Sciences Osijek
(Department of Phytomedicine)
Osijek
Defense date and country2023-09-28, Croatia
Scientific / art field,
discipline and subdiscipline		BIOTECHNICAL SCIENCES
Agronomy
Crop Production
Abstract
The research was done with the goal of proving whether mobile applications for plant identification can recognize segetal and ruderal weeds, as well as comparing which mobile applications produce the most accurate findings. The identification is based on 94 pictures of seven weed species obtained in eastern Croatia. To identify weeds, five mobile applications (PlantNet, Blossom, PlantIn, Plantum, and PlantMe) available on Google Play and the App store were employed. The PlantNet application provided the best identification result with an accuracy of 95.74%, while the PlantIn application provided the lowest identification result with an accuracy of 60.64%. In addition to the best results, the PlantNet application provides users with another significant benefit over other applications, it is free from the start and for an extended length of time.
Abstract (croatian)
Istraživanje je provedeno s ciljem da se dokaže mogu li mobilne aplikacije za identifikaciju biljaka prepoznati segetalne i ruderalne korove, te je uspoređivanje koje mobilne aplikacije pokazuju najtočnije rezultate. Identifikacija je temeljena na 94 fotografije sedam korovnih vrsta slikanih na području istočne Hrvatske. Za identifikaciju korova korišteno je pet mobilnih aplikacija (PlantNet, Blossom, PlantIn, Plantum i PlantMe) dostupnih putem Google Play-a i App store-a. Najbolji rezultat identifikacije daje aplikacija PlantNet s točnosti od 95,74 %, dok najgori rezultat identifikacije daje aplikacija PlantIn s točnosti od 60,64 %. Uz najbolji ostvaren rezultat aplikacija PlantNet nudi korisnicima još jednu veliku prednost naspram drugih aplikacija, a to je da je ona besplatna od samog početka i na daljni period korištenja.
Keywords
Keywords (croatian)
Languageenglish
URN:NBNurn:nbn:hr:151:093514
Study programmeTitle: Digital Agriculture - graduate - university
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka digitalne poljoprivrede (magistar/magistra inženjer/inženjerka digitalne poljoprivrede)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Public notegraduate thesis
Created on2023-11-16 10:57:06