Leveraging Ontologies, Context and Social Networks to Automate Photo Annotation
This paper presents an approach to semi-automate photo annotation. Instead of using content-recognition techniques this approach leverages context information available at the scene of the photo such as time and location in combination with existing photo
- PDF / 186,318 Bytes
- 4 Pages / 430 x 660 pts Page_size
- 41 Downloads / 176 Views
Abstract. This paper presents an approach to semi-automate photo annotation. Instead of using content-recognition techniques this approach leverages context information available at the scene of the photo such as time and location in combination with existing photo annotations to provide suggestions to the user. An algorithm exploits a number of technologies including Global Positioning System (GPS), Semantic Web, Web services and Online Social Networks, considering all information and making a best-effort attempt to suggest both people and places depicted in the photo. The user then selects which of the suggestions are correct to annotate the photo. This process accelerates the photo annotation process dramatically which in turn aids photo search for a wide range of query tools that currently trawl the millions of photos on the Web. Keywords: Photo annotation, context-aware, Semantic Web.
1
Introduction
Finding photos is now a major activity for Web users, but they suffer from information overload as their attempts to find the photos they want are frustrated by the enormous and increasing number of photos [1][2]. The processing speed of computers can be leveraged to perform the hard work of finding photos for the user and to thereby alleviate the information overload. To enable the machine to retrieve photos for the user, we must first examine how users mentally recall photos themselves. Research indicates that users recall photos primarily by cues in the following categories, in descending order of importance: (i) who is in the photo; (ii) where the photo was taken; and (iii) what event the photo covers [3]. Searchable description metadata in these categories can be created for photos and search engines can then match user queries with these descriptions and present the best matches to the user. A key challenge is how to create this useful, searchable description metadata about photos. Manual annotation of photos is tedious and consumes large amounts of time. Automated content-based techniques such as face recognition rely on large training sets and are dependant B. Falcidieno et al. (Eds.): SAMT 2007, LNCS 4816, pp. 252–255, 2007. c Springer-Verlag Berlin Heidelberg 2007
Leveraging Ontologies, Context and Social Networks
253
on the illumination conditions at the scene of photo capture [4]. Complimentary context-based approaches provide a lightweight, scalable solution to support the abstract way in which users actually think about photos. Section 2 introduces the implementation of just such a context-based approach: the Annotation CReatiON for Your Media (ACRONYM) prototype1 . Related Work. CONFOTO [5] is a semantic browsing and annotation service for conference photos. It combines the flexibility of the Resource Description Framework (RDF) with recent Web trends such as folksonomies, interactive user interfaces, and syndication of news feeds. PhotoCompas [6] uses timestamps and co-ordinates captured by GPS-enabled cameras to lookup higher level contextual metadata about photos from existing Web services. Given
Data Loading...
