magistrsko delo
Leon Ropoša (Author), Franc Solina (Mentor)

Abstract

V magistrski nalogi je predstavljena uporaba metod za prepoznavo obraznega izraza na problemu ugotavljanja ali je bil osebi okus zaužite hrane všeč ali ne. Trenutno obstaja nekaj raziskav, kjer so z uporabo obstoječe programske opreme, ki zazna prisotnosti šestih osnovnih čustev in nevtralnega izraza, iskali korelacijo med intenziteto zaznanih čustev in odzivom na okus hrane. V magistrski nalogi pa smo problem obravnavali kot dvorazredni, torej se na posnetku izraža prijeten ali neprijeten odziv na okus hrane. Na posnetkih odziva na okus hrane smo tudi učili uporabljeno metodo, medtem ko so v omenjenih raziskavah uporabili že naučene modele. Ločeno smo obravnavali odziv na okus hrane in odziv na okus pijače. Ker nismo našli nobene baze posnetkov okušanja, smo bazo pripravili sami. Najprej smo preizkusili nekaj metod za prepoznavo obraznega izraza na standardnih bazah, ki vsebujejo prikaz različnih čustev. Metodo, ki se je najbolje odrezala na bazah, smo potem uporabili na naši podatkovni bazi, pri čemer smo dosegli dobre rezultate. Na koncu smo še predstavili in preizkusili nekaj metod za avtomatsko ugotavljanje prekrivanja na obrazu, ki nastopi pri zajemu hrane. Pri preizkusu na naši podatkovni bazi smo namreč uporabili zgolj del posnetka, po koncu prekrivanja.

Keywords

računalniški vid;prepoznava obraznega izraza;detekcija čustev;ugotavljanje odziva na hrano;detekcija prekrivanja obraza;računalništvo;računalništvo in informatika;magisteriji;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [L. Ropoša]
UDC: 004.93(043.2)
COBISS: 1536667075 Link will open in a new window
Views: 1352
Downloads: 278
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Determination of facial emotions during food testing using computer vision methods
Secondary abstract: This master thesis presents usage of facial expression methods for the purpose of discovering food taste reaction. There are currently a few research articles where using existing software that detects six basic emotions and neutral expression, correlation between intensity of detected emotions and food taste reaction was investigated. In this theses we presented this problem as binary, so that a video shows either pleasant or unpleasant food taste reaction. We also trained our method on this data, while the existing research used pretrained data. We separately tested response of reactions on food taste and drink taste. Because we could not obtain any database of food tasting, we prepared the database ourselves. We first tested some facial expression recognition methods on standard databases, that contian several different emotions. The most successful method was then used on our database, where it performed with good results. In the last chapter of thesis, we also presented and tested methods for automatic detection of face occlusion, which is the results of food intake. While performing test on our database we only used the part of video after the end of face occlusion.
Secondary keywords: computer vision;facial expression recognition;emotion detection;food taste reaction detection;face occlusion detection;computer science;computer and information science;master's degree;
File type: application/pdf
Type (COBISS): Master's thesis/paper
Study programme: 1000471
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 96 str.
ID: 9077501