Bilkent University
Department of Computer Engineering

---

S E M I N A R

 

Automatic Tag Expansion using Visual Similarity for Photo Sharing Websites

 

Sare Gul Sevil
MSc.Student
Computer Engineering Department
Bilkent University

In this paper we describe and analyze an automatic photo tag expansion method designed for photo sharing websites. The purpose of the method is to suggest tags that are relevant to the visual content of a given photo at upload time. Both textual and visual cues are used in the process of tag expansion. When a photo is to be uploaded, the system asks for 2-3 initial tags from the user. The initial tags are used to retrieve relevant photos together with their tags. These photos are assumed to be potentially related to the uploaded photo. The tag sets of the relevant photos are used to form the candidate tag list, and visual similarity between target photo and each relevant photo is used to give weights to these candidate tags. Tags with the highest weights are suggested to the user. The method was applied on Flickr1. A user-study was conducted to evaluate the performance of the method. Results show that including visual information in the process of photo tagging increases accuracy with respect to text-based methods.

 

DATE: 20 April, 2009, Monday@ 17:00
PLACE: EA 409