Skip to Main Content
A geotagged photo refers to that a photo contains its location information where it was taken. Compared with other existing applications, we show the photo clusters instead of all photos where the number of photo clusters is much less than that of all photos. We designed a clustering algorithm that clusters geotagged photos (abbreviated as GPCA) in accordance to thresholds of different scales. In general, GPCA is an alternative of k-means clustering algorithm. Given a scale graduation of a map, the distance threshold is also determined. Before clustering geotagged photos, we use the distance threshold to decide the number of clusters. In other words, the number of centroids is chosen according to the graduation scale of a map. GPCA clusters geotagged photos into different photo clusters. Then,GPCA recomputed the new centeriods of photo clusters. GPCA executes the computation of new centeriods iteratively until all centeriods are fixed.Note that prior partition-based clustering algorithms choose an arbitrary number of initial centriods at random. Also, choosing the number of centriods is considered as an application-dependent issue. As a result, they did not guarantee that the clustering quality is not the same every time. By taking advantage of the result of using photo clusters, the performance of map-enabled photo service is improved efficiently.