Hidden Markov model for event photo stream segmentation

Jesse Prabawa Gozali, Min Yen Kan, Hari Sundaram

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A photo stream is a chronological sequence of photos. Most existing photo stream segmentation methods assume that a photo stream comprises of photos from multiple events and their goal is to produce groups of photos, each corresponding to an event, i.e. they perform automatic albuming. Even if these photos are grouped by event, sifting through the abundance of photos in each event is cumbersome. To help make photos of each event more manageable, we propose a photo stream segmentation method for an event photo stream - the chronological sequence of photos of a single event - to produce groups of photos, each corresponding to a photo-worthy moment in the event. Our method is based on a hidden Markov model with parameters learned from time, EXIF metadata, and visual information from 1) training data of unlabelled, unsegmented event photo streams and 2) the event photo stream we want to segment. In an experiment with over 5000 photos from 28 personal photo sets, our method outperformed all six baselines with statistical significance (p < 0.10 with the best baseline and p < 0.005 with the others).

Original languageEnglish (US)
Title of host publicationProceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012
Pages25-30
Number of pages6
DOIs
StatePublished - Oct 4 2012
Externally publishedYes
Event2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012 - Melbourne, VIC, Australia
Duration: Jul 9 2012Jul 13 2012

Publication series

NameProceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012

Other

Other2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012
Country/TerritoryAustralia
CityMelbourne, VIC
Period7/9/127/13/12

Keywords

  • Event photo stream segmentation
  • digital photo library
  • hidden Markov model

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Hidden Markov model for event photo stream segmentation'. Together they form a unique fingerprint.

Cite this