Inferring photographic location using geotagged web images

Joshi, Dhiraj; Gallagher, Andrew; Yu, Jie; Luo, Jiebo
January 2012
Multimedia Tools & Applications;Jan2012, Vol. 56 Issue 1, p131
Academic Journal
Geotagging has become a recent phenomenon that allows users to visualize and manage photo collections in many new and interesting ways. Unfortunately, manual geotagging of a large collection of pictures on the globe is still a time-consuming and laborious task even though geotagging devices are gradually being adopted. At the same time, there exist billions of legacy pictures taken before the onset of geotagging. In recent times, large collections of Web images have been found to facilitate a number of image understanding tasks including geolocation estimation. In this paper, we leverage user tags along with image content to infer the geolocation of images. Our model builds upon the fact that the visual content and user tags of pictures can together provide significant hints about their geolocations. Using a collection of over a million geotagged pictures, we build location probability maps for commonly used image tags over the entire globe. These maps reflect the collective picture-taking and tagging behaviors of thousands of users from all over the world. We further study the geographic entropy and frequency of user tags as geo-inference features and investigate the usefulness of using these features for selecting geographically meaningful annotations. On the other hand, visual content matching is performed using multiple feature descriptors including tiny images, color histograms, GIST features, and bags of textons. Finally, visual KNN matching based geographic mapping scheme is integrated with tag location probability maps to form a strong geo-inference engine. Experiments have shown improvements over geolocation inference performed using either modality alone.


Related Articles

  • Geotag propagation in social networks based on user trust model. Ivanov, Ivan; Vajda, Peter; Lee, Jong-Seok; Goldmann, Lutz; Ebrahimi, Touradj // Multimedia Tools & Applications;Jan2012, Vol. 56 Issue 1, p155 

    In the past few years sharing photos within social networks has become very popular. In order to make these huge collections easier to explore, images are usually tagged with representative keywords such as persons, events, objects, and locations. In order to speed up the time consuming tag...

  • Semantic Based Image Annotation Using Descriptive Features and Retagging approach. Nagarani, P.; VenkataRamanaChary, R.; Lakshmi, D. Rajya // International Journal of Multimedia & Its Applications;Feb2012, Vol. 4 Issue 1, p15 

    The Semantic based annotation of an image is very important and a difficult task in content-based image retrieval (CBIR). The low-level features of the images are described using color and the texture features and the proposed model is used for semantic annotation of images. Also the textual...

  • Categorical and specificity differences between user-supplied tags and search query terms for images. An analysis of Flickr tags and Web image search queries. Chung, EunKyung; Yoon, JungWon // Information Research;Sep2009, Vol. 14 Issue 3, Special Section p1 

    Introduction. The purpose of this study is to compare characteristics and features of user-supplied tags and search query terms for images on the Flickr Website in terms of categories of pictorial meanings and level of term specificity. Method. This study focuses on comparisons between tags and...

  • Informative Tagging of Images: The Importance of Modality in Interpretation. Rafferty, Pauline // Knowledge Organization;2011, Vol. 38 Issue 4, p283 

    The term "tagging" is widely used for the assigning of terms to information objects in user-driven websites, although a cursory examination of such websites suggests that the communicative functions undertaken by taggers are not always driven by concerns about inter-subjective informative...

  • Rediscovery of forgotten images in domestic photo collections. Frohlich, David; Wall, Steven; Kiddle, Graham // Personal & Ubiquitous Computing;Apr2013, Vol. 17 Issue 4, p729 

    The exponential growth of digital photo collections, combined with the legacy of printed photographs, is leading families to experience difficulties in remembering and finding photographs. Paradoxically this creates new opportunities for the rediscovery of forgotten images. This paper reports a...

  • An approach of image semantic automatic tagging based on SVM. Fu Juchun // Applied Mechanics & Materials;2014, Issue 530-531, p382 

    To find the need of images from Internet is a heavy work, image annotation techniques can be used to help us quickly find the required images, the traditional image annotation method can't between the image and text classification, cannot achieve most web users demand, this paper proposes an...

  • Visually weighted neighbor voting for image tag relevance learning. Lee, Sihyoung; Neve, Wesley; Ro, Yong // Multimedia Tools & Applications;Sep2014, Vol. 72 Issue 2, p1363 

    The presence of non-relevant tags in image folksonomies hampers the effective organization and retrieval of user-contributed images. In this paper, we propose to learn the relevance of user-supplied tags by means of visually weighted neighbor voting, a variant of the popular baseline neighbor...

  • Expressive Bibliography: Personal Collections in Public Space. Feinberg, Melanie // Knowledge Organization;2011, Vol. 38 Issue 2, p123 

    This paper examines collections of citations that individual users contribute to social tagging systems such as Delicious and LibraryThing. I characterize these personal collections, furnished with various forms of metadata and arranged for Web display, as a means of communication, where a...

  • Tags are messy and useful. WEINBERGEB, DAVID // KM World;Feb2014, Vol. 23 Issue 2, p1 

    In this article the author talks about the usefulness and messiness of social media tags. It mentions several benefits of using tags in terms of organizing topics and cites their importance when they were first introduced on the Web in the early 2000s. It also discusses the problems associated...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics