social images summerization
Khaire Sujata,Waghmode Vaishali,Ingale Bhagyashri,Shinde Priyanka
Published in International Journal of Advanced Research in Computer Science Engineering and Information Technology
ISSN: 2321-3337 Impact Factor:1.521 Volume:4 Issue:3 Year: 11 April,2015 Pages:397-407
Abstract
In our proposed approach Geo-tagging concept is introduced. Geo-tagging gives scope for attaching location-specific information to the photograph that information is in the form of longitude and latitude coordinates. In this paper introducing a novel approach to create automatic visual summaries of Geo-tagged images that containing visual summery such as color, texture, user tags, description etc. With the help of visual summary and metadata of an image we represent the diverse and representative images of specific geographic area. In proposed system the input from user as searching a location based on input location the proposed system create a certain radius around the location with the help of random walk with restart RWR concept construction of the graph that builds the relation between each image node and extract the visual feature and metadata of an images after that introducing edge weight mechanism which calculates the similarities and dissimilarities between image nodes and represent the most diverse and representative images set. This is simple and effective approach that helps to user to decide whether he/she visit a particular location or not. This approach uses only Geo-coordinates for making visual summery so it gives advantage over human annotation.
Kewords
Geo-tagging, Flickr, image clustering, graph-based models, Visual diversity, RWR, visual summarization of geographic areas.
Reference
[1] J. Carbonell and J. Goldstein, ―The use of mmr, diversity-based reranking for reordering documents and producing summaries,‖ in Proc. 21st Annu. Int. ACM SIGIR Conf. Res. Develop. Inf., Retrieval, 1998, pp. 335–336. [2] L. S. Kennedy and M. Naaman, ―Generating diverse and representative image search results for landmarks,‖ in Proc. 17th Int. Conf. World Wide Web, 2008, pp. 297–306.932 IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 15, NO. 4, JUNE 2013 [3] R. H. van Leuken, L. Garcia, X. Olivares, and R. Zwol, ―Visual diversification of image search results,‖ in Proc. 18th Int. Conf. World Wide Web, 2009, pp. 341–350. [4] K. Song, Y. Tian, W. Gao, and T. Huang, ―Diversifying the image retrieval results,‖ in Proc. 14th Annu. ACM Int. Conf. Multimedia, 2006, pp. 707–710. [5] A. Strehl and J. Ghosh, ―Cluster ensembles—A knowledge reuse framework for combining multiple partitions,‖ J. Mach. Learning Res., vol. 3, pp. 583–617, Dec. 2002. [6] S. Rudinac, A. Hanjalic, and M. Larson ―Generating Visual Summaries of Geographic Areas Using Community-Contributed Images‖ in IEEE Transaction on Multimedia 15(4), June 2013, pp. 921-932. [7] www.flickr.com
