A clustering method for concurrent photos obtained from multiple cameras using max-flow network model

Abstract

With the popularization of digital cameras, the use of several cameras by group photographers at the same event is becoming common. Photographers can share their contents and even take pictures of each other. So it is becoming important to manage concurrent photos from multiple cameras in order to classify many accumulated photos into proper clusters. In this paper, we propose a novel photo clustering method based on the max-flow network algorithm, and we visualize a network graph for cluster verification. To apply our algorithm, input concurrent photos are used to create an edge-weighted graph structure. In order to transform the photo clustering problem into a graph partition one, first we need to construct an Augmented Concurrent photo Graph (ACG) and then rewrite our original problem in terms of the graph partition one using the min-cut max-flow network model. The previous methods dealt with photo clustering as a 1-D problem using a linear partition. But we consider clustering for concurrent group photos as a 2-D partition based on other users' photo contents. Each photo is used to create a node and similarities between photos are used to create the edge weights (capacities) of the network. We partition the network into two subgraphs according to the min-cut, which represents the weakest edge connections between the photos. Using repeated graph partitions for each subgraph (sub-network), we can obtain suitable subgraphs corresponding to photo clusters. The graph construction or partition can be adjusted according to user preferences in order to obtain the intended results.Keywords Photo clustering Á Maximum flow Á Network model Á EXIF MotivationCurrently, the digital camera is so popular that many households have one or more. Moreover, the main storage medium of the digital camera, flash memory, is becoming cheaper as its capacity increases. In contrast to the analogue film camera, after shooting, digital camera users can select the photos they want while still in front of their computer or camera. The convenience of digital cameras makes it easy for people to take photographs regardless of cost or redundancy. Therefore, digital camera owners tend to take more photos than film camera owners.There are two issues in digital photo management. The first is dealing with the massive number of highly related photos. Usually a user takes at least a hundred photos each time they travel or attend an event, and an intensive user may take thousands of photos. Since the number of photos a user must classify is so large, most people find this boring and time-consuming work. The previous studies on photo management focused on this point and are designed for clustering photos from a single user's photo collection via temporal or spatial analysis. But the patterns of concurrent group photos can vary according to the photographers and so we have to deal with various kinds of input photos.The second issue we focus on is extracting the relationships between group photos. With the increased popularity of digital cameras, it is in...