Personal photo indexing (original) (raw)

PhotoMap: from location and time to context-aware photo annotations

Journal of Location Based Services, 2008

Despite the growth of geotagged multimedia data on the Web, spatial and temporal metadata are still poorly exploited by Web search engines and multimedia systems. Interpretation and inference processes can enlarge these metadata towards high quality information that are useful for annotating multimedia automatically. In this paper, we propose a semi-automatic approach for annotating personal photos based on the use of OWL-DL ontologies together with the next generation of mobile devices. We present an ontology called ContextPhoto and a contextual photo annotation approach which improve the development of more efficient personal image management tools. ContextPhoto provides concepts for representing captured and inferred context information reusing Web standards that describes spatial, temporal and social networking data. In order to validate the context annotation process we propose, we have also designed and developed a mobile and Web location-based system. This new system, called PhotoMap, is an evolution of the related mobile annotation systems since it provides automatic annotation about the spatial, temporal and social contexts of a photo. We also present a demonstration of the PhotoMap application during a tourist tour in the city of Rome.

Context-based Media Geotagging of Personal Photos

2013

This paper addresses the problem of automatic geotagging of media within the context of a personal media collection. In contrast with textual and visual methods which tackle the same problem we approach it focusing on analysis of contextual information. An event as a context aggregator plays the central role in our approach. The proposed method automatically estimates geographical coordinates (latitude and longitude) within the temporal boundaries of events computed from a personal media collection. Proposed framework interpolates or extrapolates GPS information rely on geoannotated media entities from the collection. The process of interpolation is automatically performed by the framework based on temporal distances between samples in combination with using free on-line navigation service. All this leads to a new cost efficient and intelligible event-centered way to enrich the collection with geographical information. Experimental results show that we are able to assign geographical coordinates for 83% of images within an error of 5 km.

PhotoMap – Automatic Spatiotemporal Annotation for Mobile Photos

Lecture Notes in Computer Science, 2007

The amount of photos in personal digital collections has grown rapidly making their management and retrieval a complicated task. In addition, existing tools performing manual spatial and content annotation are still time consuming for the users. To annotate automatically these photos using mobile devices is the emerging solution to decrease the lack of the description in photo files. In this context, this paper proposes a mobile and location-based system, called PhotoMap, for the automatic annotation and the spatiotemporal visualization of photo collections. PhotoMap uses the new technologies of the Semantic Web in order to infer information about the taken photos and to improve both the visualization and the retrieval. We also present a demonstration of the PhotoMap application during a tourist tour in the city of Grenoble.

Hierarchical photo organization using geo-relevance

Proceedings of the 15th annual ACM international symposium on Advances in geographic information systems - GIS '07, 2007

a) (b) (c) Figure 1: Organizing image collections. (a) Typical unorganized display of thumbnails. (b) Images organized according to camera positions (GPS). (c) The proposed hierarchical organization allows meaningful image browsing according to scene semantics. Note that images of the same object may appear at random positions in (a), in different positions based on the camera location in (b) but are placed in the same sub-tree in (c).

Modeling Characteristics of Location from User Photos

Proceedings of the 2017 ACM Workshop on Theory-Informed User Modeling for Tailoring and Personalizing Interfaces

In the past decade, location-based services have grown through geo-tagging and place-tagging. Proliferation of GPS-enabled mobile devices further enabled exponential growth in geotagged user content. On the other hand, location-based applications harness the abundance of geo-tagged content to further improve user experience and more relevant localized content. We show in this paper that geo-tagged content can vary significantly based on whether they are captured by a local versus a tourist to the location. Using photos shared by online users, we also show how we can learn unique characteristics about a given location. We finally discuss an effective metric to rank the most representative photos for a given location by combining visual contents and their social engagement potential.

Position-annotated photographs: A geotemporal web

2003

Abstract With the advent of digital cameras, photographs are no longer gathering dust, forgotten in old shoeboxes. Instead, they are lying unused in hard disk dircctories and on CDs. The Geotemporal Web system, belonging to the" capture and access" class of ubiquitous computing applications, addresses this phenomenon by automatically converting raw data from the typical vacation trip into a lively Web site.

ContextSeer: context search and recommendation at query time for shared consumer photos

2008

The advent of media-sharing sites like Flickr has drastically increased the volume of community-contributed multimedia resources on the web. However, due to their magnitudes, these collections are increasingly difficult to understand, search and navigate. To tackle these issues, a novel search system, ContextSeer, is developed to improve search quality (by reranking) and recommend supplementary information (i.e., search-related tags and canonical images) by leveraging the rich context cues, including the visual content, high-level concept scores, time and location metadata. First, we propose an ordinal reranking algorithm to enhance the semantic coherence of text-based search result by mining contextual patterns in an unsupervised fashion. A novel feature selection method, wc-tf-idf is also developed to select informative context cues. Second, to represent the diversity of search result, we propose an efficient algorithm cannoG to select multiple canonical images without clustering. Finally, ContextSeer enhances the search experience by further recommending relevant tags. Besides being effective and unsupervised, the proposed methods are efficient and can be finished at query time, which is vital for practical online applications. To evaluate ContextSeer, we have collected 0.5 million consumer photos from Flickr and manually annotated a number of queries by pooling to form a new benchmark, Flickr550. Ordinal reranking achieves significant performance gains both in Flcikr550 and TRECVID search benchmarks. Through a subjective test, cannoG expresses its representativeness and excellence for recommending multiple canonical images. be obtained by feature extractors

Automatic Organization of Photograph Collections

In this paper we address the problem of interacting with large streams of photographs. To achieve this, we studied patterns of photography, and found that photo streams exhibit a strong burst pattern along multiple levels of the time line. Using this fact we developed an algorithm to automatically organize the photographs hierarchically, where each node corresponds to a different event that the photographs capture. In order to represent the hierarchy, a small number of photographs are automatically selected to represent that event. This selection is modeled on the results of an ethnography we conducted to determine how human carry out this task. Using these methods, we have developed applications for viewing, tagging, and searching large streams of digital photographs.