Using Photo Similarity and Weighted Graphs for the Temporal Synchronization of Event-Centered Multi-User Photo Collections

Abstract

This paper describes a method to temporally align photo collections that have been created during the same event by different users using their own unsynchronized digital photo capture devices. Using multiple similarity measures, we identify pairs of similar photos from different collections. We then temporally align the photo collections by traversing a graph, whose nodes represent the collections, and edges represent the similar photo pairs between collections. Outcome of this process is a set of modified timestamps for the photos, which could be used in applications such as time-based clustering and sub-event detection in multi-user photo collections. We evaluate the proposed synchronization method on benchmark datasets and we compare it to state-of-the-art methods, demonstrating its superiority.