Detekcija i lokalizacija kontura

master's thesis

• Title (english): Contour detection and localization
• Author: Veronika Bubnjar
• Mentor: Tomislav Stipančić (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2024-07-15, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing; Data Processing

Abstract

U diplomskom radu objašnjeni su i primijenjeni koraci algoritama za detekciju rubova i kontura na slikama. Objašnjena je važnost detekcije kontura kao jednog od bitnih segmenata računalnog vida. Detaljnije su objašnjeni modeli detekcije kao što su Canny, Sobel, Roberts i Prewitt. Implementacijom koraka kroz odabrane modele se uspoređuju i analiziraju dobiveni rezultati. Razvijena programska rješenja su temeljena na OpenCV biblioteci implementirani kroz Python programski jezik

Abstract (english)

In this thesis, the steps of algorithms for edge and contour detection in images are explained and applied. The importance of contour detection as one of the crucial segments of computer vision is discussed. Detection models such as Canny, Sobel, Roberts, and Prewitt are explained in detail. By implementing the steps through the chosen models, the obtained results are compared and analyzed. The entire process is carried out in Python using OpenCV.

• Keywords: Računalni vid; detekcija rubova; detekcija kontura; Canny; Sobel; Roberts; Prewitt
• Keywords (english): Computer vision; edge detection; contour detection; Canny; Sobel; Roberts; Prewitt
• Language: croatian
• URN:NBN: urn:nbn:hr:235:669989
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-07-19 15:01:38