Određivanje veličine ribe iz slike

undergraduate thesis

• Title (english): Determining Fish Size from an Image
• Author: Ana-Marija Rukavina
• Mentor: Nikola Mišković (mentor)
• Committee member: Nikola Mišković (predsjednik povjerenstva)
• Committee member: Antonio Vasilijević (član povjerenstva)
• Committee member: Filip Mandić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2016-09-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

U akvakulturi je od velike važnosti poznavati veličinu ribe kako bi se mogla odrediti optimalna količina hrane koja je potrebna za dostizanje željene veličine ribe. Dok se trenutno veličina ribe određuje uzimanjem uzoraka ribe iz kaveza, naprednije metode uključuju neometano snimanje riba i određivanje veličine. U sklopu završnog rada potrebno je istražiti algoritme obrade slike koji se mogu koristiti za određivanje veličine ribe. Potrebno je iskoristiti veliki broj slika koje su snimljene u stvarnom ribogojilištu i koje su dostupne u Laboratoriju za podvodne sustave i tehnologije te predložiti najbolji postupak za određivanje veličine riba. Dobivene rezultate je potrebno usporediti s ručno dobivenim očitanjem veličine.

Abstract (english)

In aquaculture, it's of great importance to know the size of a fish to be able to determine the optimum amount of food necessary for the fish to achieve a targeted size. Currently, the most used technique would be taking samples and measuring the fish manually. However, a more advanced method, in which the fish would remain undisturbed, would be recording them and then determinating their size from images. As part of this BSc thesis, various image processing algorithms are examined in order to be implemented in determinating fish size. It's required to use a large number of images taken in an actual fish farm, that are available in the Laboratory for Underwater Systems and Technologies and then suggest the best procedure to determine the fish size. The acquired results have to be compared to manually obtained fish size measurements.

• Keywords: obrada slike; veličina ribe; Matlab; podudaranje po predlošku
• Keywords (english): image processing; fish size; Matlab; template matching
• Language: croatian
• URN:NBN: urn:nbn:hr:168:929489
• Study programme: Title: Electrical Engineering and Information Technology; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 11:38:20