Strojno učenje za detekciju i prepoznavanje lica

master's thesis

• Title (english): Machine learning for face detection and recognition
• Author: Toma Vlahović
• Mentor: Sanja Seljan (mentor)
• Committee member: Ivan Dunđer (predsjednik povjerenstva)
• Committee member: Vjera Lopina (član povjerenstva)
• Committee member: Sanja Seljan (član povjerenstva)
• Granter: University of Zagreb; Faculty of Humanities and Social Sciences; (Department of information and Communication sciences); Zagreb
• Defense date and country: 2024-09-26, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences; Organization and Informatics

Abstract

Cilj ovog rada bio je izrada sustava za detekciju lica i prepoznavanje tona kože te primjenu odgovarajućeg zaštitnog faktora.
Teorijski dio daje pregled definicije i opisa umjetne inteligencije, područja u kojima se koristi te razvoj i područja primjene umjetne inteligencije, s osobitim naglaskom na računalni vid. Analizirane su vrste strojnog učenja i primjena u različitim istraživanjima i svakodnevnici. Posebno su analizirane neuronske mreže, koje predstavljaju temelj dubokog učenja, koje ima sposobnost učiti iz većih količina podataka bez ljudske intervencije. Prikazane su faze procesa detekcije lica, tehnologije koje se primjenjuju i primjeri upotrebe računalnog vida.
U praktičnom dijelu ovog rada prikazan je postupak za detekciju lica koji je integriran s prepoznavanjem tona kože i preporukom za odgovarajući zaštitni faktor. Program je napisan u programskom jeziku pythonu koji pokazuju rezultate prepoznatog lica, tona kože i preporuke zaštitnog faktora.

Abstract (english)

The main goal of this work was to develop a system for face detection and skin tone recognition and the application of an appropriate protective factor.
The theoretical part provides an overview of the definition and description of artificial intelligence, the areas in which it is used and the development and application areas of artificial intelligence, with a special emphasis on computer vision. The types of machine learning and their application in various researches and everyday applications are analyzed. In particular, neural networks were analyzed, which represent the basis of deep learning, which has the ability to learn from large amounts of data without human intervention. The phases of the face detection process, the technologies that are applied and examples of the use of computer vision are presented.
In the practical part of this work, a procedure for face detection is presented, which is integrated with skin tone recognition and a recommendation for the appropriate protective factor. The program is written in the Python programming language, which shows the results of the recognized face, skin tone and protective factor recommendations.

• Keywords: umjetna inteligencija; strojno učenje; duboko učenje; detekcija lica; prepoznavanje lica
• Keywords (english): artificial intelligence; machine learning; deep learning; face detection; face recognition
• Language: croatian
• URN:NBN: urn:nbn:hr:131:217997
• Study programme: Title: Information Sciences; specializations in: Archivistics Study, Library Science, Information Sciences (research), Information Sciences (teaching), Museology and heritage management, Informatology; Course: Information Sciences (research); Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra informacijskih znanosti (magistar/magistra informacijskih znanosti)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-10-01 16:18:33