Event classification for personal photo collections

Abstract

People take more and more photos at different time and different events, however, these photos are often put into one giant folder and they are seldom annotated or organized. As the result, people often find it difficult to find photos they want. The problem of media organization and management of such personal photo collections is becoming a much more pressing issue. Event is one of the most important elements of people's life and memories. Such events include Christmas, Halloween parties, Birthday parties, sports match, beach fun, etc. A collection of an event typically consists of a series of photos that constitute the event. Automatic classification of photo collections into pre-defined event types is of critical importance to personal photo management. In this paper, we propose a system that utilizes metadata embedded into each photo as well as the visual features describing the image content to classify each photo. In order to aggregate the information from individual photos to obtain the collection level event annotation, we propose a probabilistic fusion framework that integrates the prediction from individual photos to obtain the collection level prediction. The proposed approach is designed to be scalable so that adding new event categories do not need algorithm redesign. Experiments show promising results of the approach.