People in photos
Numminen, Jyrki (2013)
2013
Signaalinkäsittelyn ja tietoliikennetekniikan koulutusohjelma
Tieto- ja sähkötekniikan tiedekunta - Faculty of Computing and Electrical Engineering
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Hyväksymispäivämäärä
2013-12-04
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tty-201312181496
https://urn.fi/URN:NBN:fi:tty-201312181496
Tiivistelmä
As digital cameras and camera equipped smart phones have become commonplace both the needs and the opportunities to automatically categorize photographs have increased. The subject has been researched with several goals in mind, for example how to find family relations in group photos or how to categorize a groups of people by their subculture.
This thesis was made for Tampere University of Technology (TUT) department of signal processing in 2013. In this thesis I review and analyze recent research into face and face properties recognition. Specifically methods of identifying individuals identity, age, gender and expression from known data sets for labeling purposes are considered. Additionally labeling methods of photo categorization based on groups of people in them are examined. Based on this analysis I then constructed an example implementation of these methods as a part of a camera application on Android mobile platform. Finally the suggested methods are evaluated in terms of practical usability.
This thesis was made for Tampere University of Technology (TUT) department of signal processing in 2013. In this thesis I review and analyze recent research into face and face properties recognition. Specifically methods of identifying individuals identity, age, gender and expression from known data sets for labeling purposes are considered. Additionally labeling methods of photo categorization based on groups of people in them are examined. Based on this analysis I then constructed an example implementation of these methods as a part of a camera application on Android mobile platform. Finally the suggested methods are evaluated in terms of practical usability.