prikaz prve stranice dokumenta Industrijski sustav vizije za primjenu u robotici
Access restricted to students and staff of home institution
master's thesis
Industrijski sustav vizije za primjenu u robotici
Rijeka: University of Rijeka, Faculty of Engineering, 2019. urn:nbn:hr:190:767235
Abdulaj, Marko
University of Rijeka
Faculty of Engineering
Department of Automation and Electronics
Section of Electronics, Robotics and Automation

Institutional repository: Repository of the University of Rijeka, Faculty of Engineering

Cite this document

Abdulaj, M. (2019). Industrijski sustav vizije za primjenu u robotici (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:767235

Abdulaj, Marko. "Industrijski sustav vizije za primjenu u robotici." Master's thesis, University of Rijeka, Faculty of Engineering, 2019. https://urn.nsk.hr/urn:nbn:hr:190:767235

Abdulaj, Marko. "Industrijski sustav vizije za primjenu u robotici." Master's thesis, University of Rijeka, Faculty of Engineering, 2019. https://urn.nsk.hr/urn:nbn:hr:190:767235

Abdulaj, M. (2019). 'Industrijski sustav vizije za primjenu u robotici', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 30 November 2024, https://urn.nsk.hr/urn:nbn:hr:190:767235

Abdulaj M. Industrijski sustav vizije za primjenu u robotici [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2019 [cited 2024 November 30] Available at: https://urn.nsk.hr/urn:nbn:hr:190:767235

M. Abdulaj, "Industrijski sustav vizije za primjenu u robotici", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:190:767235

Metadata
TitleIndustrijski sustav vizije za primjenu u robotici
Title (english)Industrial vision system for robotics
AuthorMarko Abdulaj
MentorZlatan Car (mentor)
Committee memberViktor Sučić (predsjednik povjerenstva)
Committee memberSaša Vlahinić (član povjerenstva)
Committee memberRene Prenc (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Automation and Electronics)
(Section of Electronics, Robotics and Automation)
Rijeka
Defense date and country2019-09-24, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Abstract
Cilj ovog rada je predstaviti konceptualno rješenje industrijskog sustava vizije za detekciju, klasifikaciju i lokalizaciju objekta u proizvodnji. U radu su obrađene metode digitalne obrade slike kojima su podvrgnuti skupovi za treniranje modela neuronske mreže. S obzirom na vizualne karakteristike objekta za rješenje problema klasifikacije u ovom radu kao algoritam umjetne inteligencije korištena je konvolucijska neuronska mreža. Točnost klasifikacije postignuta modelima neuronske mreže uvelike je ovisila o digitalnoj pred obradi slika iz skupa za učenje te primjeni algoritma augmentacije za proširenje podataka. Za određivanje lokalizacije korišten je Canny operator za detekciju ruba radi što bolje aproksimacije konture. Koordinate hvatišta određene su provedbom PCA analize.
Abstract (english)
The aim of this paper is to present a conceptual solution of an industrial vision system for the detection, classification and localization of an object in production. The paper deals with the methods of digital image processing that have been subjected to training sets for neural network models. Considering the visual characteristics of the object, a convolution neural network was used as a solution to the classification problem in this paper as an artificial intelligence algorithm. The classification accuracy achieved by neural network models depended heavily on digital pre-processing of learning set images and the application of augmentation algorithm to extend data. The Canny edge detection operator was used to determine the localization for the best possible contour approximation. The capture coordinates were determined by performing PCA analysis.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:767235
Study programmeTitle: Electrical Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike (magistar/magistra inženjer/inženjerka elektrotehnike)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2020-07-02 12:28:48