Programska biblioteka za izradu ortogonalne projekcije jednostavnih pravokutnih objekata prepoznatih korištenjem programske biblioteke OpenCV

master's thesis

• Title (english): A program library for creating orthogonal projections of simple rectangular objects recognized by using OpenCV
• Author: Leon Hrnjak
• Mentor: Boris Milašinović (mentor)
• Committee member: Boris Milašinović (predsjednik povjerenstva)
• Committee member: Igor Mekterović (član povjerenstva)
• Committee member: Ljiljana Brkić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-07-03, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U sklopu ovoga rada napravljen je kratki pregled osnova OpenCV biblioteke te su izrađene programska biblioteka i demo aplikacija za crtanje ortogonalne projekcije objekata prepoznatih korištenjem OpenCV programske biblioteke. Detaljno su opisani koraci prepoznavanja objekata, algoritmi korišteni u sklopu istih te problemi koji utječu na preciznost krajnjeg rezultata. Dodatno, opisani su problemi zbog kojih prepoznavanje određenih objekata nije moguće s dovoljno dobrom preciznošću. Za kraj je napravljena analiza preciznosti generirane ortogonalne projekcije sa stvarnim vrijednostima.

Abstract (english)

A brief summary of the OpenCV library was created as part of this work, along with the library and the demo application for drawing an orthogonal projection of objects recognized using the OpenCV library. Object recognition steps, algorithms used as part of these steps and problems which affect the end results were described. Additionally, problems which prevent recognition of certain objects with enough accuracy were described. In the end, accuracy analysis was made for the generated orthogonal projections.

• Keywords: OpenCV; računalni vid; ortogonalna projekcija; tehničko crtanje; prepoznavanje rubova; prepoznavanje kontura; prepoznavanje značajki; mjerenje objekata; Android
• Keywords (english): OpenCV; computer vision; orthogonal projection; technical drawing; edge recognition; contour recognition; feature recognition; object measuring; Android
• Language: croatian
• URN:NBN: urn:nbn:hr:168:832642
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2020-01-07 18:27:44