Smile detection

Katja Rus (2012) Smile detection. EngD thesis.

Preview

Abstract

Facial expressions are one of the most powerful and indirect means of transferring feelings, cognitive status, ulterior motive and opinion among people. Considering their significance it is reasonable to expect that the development of tools recognizing facial expressions would have a big effect on everyday life. In the past years, the developers have made big progress on the development of classifiers that are needed for this kind of expression detection; however there is still a great gap between real life situations and laboratory experiments. This thesis is focused on researching the existing algorithms of smile detection, for which face detection must be executed beforehand. Various approaches, methods and databases that are being used will be presented and the development of two systems, proved to be most efficient, will be explained. In conclusion the functioning of smile detection on a simple computer program will be presented.

Item Type:

Thesis (EngD thesis)

Keywords:

facial expressions, recognition, database, machine learning algorithms

Number of Pages:

Language of Content:

Slovenian

Mentor / Comentors:

Name and Surname	ID	Function
viš. pred. dr. Borut Batagelj	298	Mentor

Link to COBISS:

http://www.cobiss.si/scripts/cobiss?command=search&base=50070&select=(ID=00009057108)

Institution:

University of Ljubljana

Department:

Faculty of Computer and Information Science

Item ID:

1628

Date Deposited:

16 Mar 2012 21:37

Last Modified:

05 Apr 2012 17:06

URI:

http://eprints.fri.uni-lj.si/id/eprint/1628

Actions (login required)

View Item