master's thesis
Cloud-based software solution for face detection and analysis of collected data

Ivan Marković (2016)
Metadata
TitleProgramsko rješenje prepoznavanja lica i analize prikupljenih podataka u oblaku računala
AuthorIvan Marković
Mentor(s)Josip Job (thesis advisor)
Abstract
U ovom diplomskom radu osmišljen je i programski analiziran sustav za analiziranje fotografija, odnosno prepoznavanje lica osoba koje se nalaze na fotografiji. Cilj sustava je ponuditi korisnicima prijenos fotografija u sustav, koje se potom analiziraju koristeći uslugu Microsoft Azure Cognitive Services. Glavni fokus ovog rada je na izradi skalabilnog rješenja u oblaku računala koje koristi dvije različite role: Worker Role i Web Role. Ideja iza dvije role je omogućiti visoku dostupnost usluge krajnjem korisniku na način da Web rola zaprima zahtjeve a worker rola u pozadini obrađuje te zahtjeve. Komunikacija između rola ostvarena je korištenjem redova. Korištene usluge u oblaku računala su : Azure Cognitive Services, Azure Cloud Services, Azure Blob Storage, Azure Queue Storage, Azure SQL Database. Analiza prikupljenih podataka ostvarena je alatom Power BI.
Keywordscloud computing photo analysis scalable architecture web system
Parallel title (English)Cloud-based software solution for face detection and analysis of collected data
Committee MembersJosip Job (committee chairperson)
Časlav Livada (committee member)
Krešimir Romić (committee member)
GranterSveučilište Josipa Jurja Strossmayera u Osijeku
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek
Lower level organizational unitsZavod za programsko inženjerstvo
Katedra za vizualno računarstvo
PlaceOsijek
StateCroatia
Scientific field, discipline, subdisciplineTECHNICAL SCIENCES
Computing
Program Engineering
Study programme typeuniversity
Study levelgraduate
Study programmeGraduate University Study Programme in Computer Engineering
Academic title abbreviationmag.ing.comp.
Genremaster's thesis
Language Croatian
Defense date2016-07-04
Parallel abstract (English)
In this work a system for face detection and analysis of photos has been designed and realized. The aim of system is to offer users a possibility for uploading photos, which are then analyzed using Microsoft Azure Cognitive Services. The main focus in this work is scalable architecture in cloud which is composed of two roles: Worker role and Web role. The idea behind these two roles is to provide high available system for end user in which web role is used for uploading photos and worker role is used for doing background processing of photos. Communication between two roles is realized using queues. Used cloud services are: Azure Cognitive Services, Azure Cloud Services, Azure Blob Storage, Azure Queue Storage and Azure SQL Database. The analysis of collected date is realized using Power BI tool.
Parallel keywords (Croatian)oblak računala analiza fotografija skalabilna arhitektura web sustav.
Resource typetext
Access conditionOpen access
Terms of usehttp://rightsstatements.org/vocab/InC/1.0/
URN:NBNhttps://urn.nsk.hr/urn:nbn:hr:200:499953
CommitterAnka Ovničević