The International Arab Journal of Information Technology (IAJIT)


Binding Semantic to a Sketch Based Query Specification Tool

 In image retrieval systems, user information needs  is expressed using multiple types of query. Unfortunately, due to  user  subjectivity  perception  to  visual  features  and   semantic  depths  of  images,  the  conventional  query  submitted  to  the  system  encounter  difficulties  to  identify  user  information   need.  The  blooming  of  interest  in  semantic  image  r etrieval  requires  current  research  direction  to  be  more  concerned  into  semant ics.  This  paper  describes  our  on-going  research  work  in  formulating  a  new  query  approach  for  image  databases.  The  enablin g  technologies  of  the  semantic  web  formed  the  building  blocks  of  our  query  specification.  Using  the  MRML  as  the  communic ation  protocol,  XML  in  the  form  of  SVG  as  the  visual  content  description (sketch based) and RDF for binding the  semantic meanings of images, this research provides  an initial framework  towards semantic based query formulation framework.    

[1] Antani S., Kasturi R., and Jain R., A Survey on the Use of Pattern Recognition Methods for Abstraction Indexing and Retrieval of Images and Video, Journal of Pattern Recognition Society , vol. 35, no. 4, pp. 945-965, 2002.

[2] Ashley J., Barber R., Flickner M., Hafner J., Lee D., Niblack W., and Petkovic D., Automatic and Semiautomatic Methods for Image Annotation and Retrieval in Query by Image Content (QBIC), in Proceedings of Storage and Retrieval for Image and Video Databases III , pp. 24-35, UAS, 1995

[3] Bradshaw B., Semantic Based Image Retrieval: A Probabilistic Approach, in Proceedings of the 8 th ACM International Conference on Multimedia , pp. 167-176, USA, 2000.

[4] Carson C., Belongie S., Greenspan H., and Malik J., Blobworld: Image Segmentation Using Expectation-Maximization and its Application to Image Querying, IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 24 no. 8, pp. 1026-1038, 2002.

[5] Chang F., Thomas H., and Yong R., Image Retrieval: Current Techniques, Promising Directions and Open Issues, Journal of Visual Communication and Image Representation , vol. 10, no. 4, pp. 39-62, 1999.

[6] Carneiro G., Chan B., Moreno J., and Vasconcelos N., Supervised Learning of Semantic Classes for Image Annotation and Retrieval, IEEE Transactions on Pattern Analysis & Machine Intelligence , vol. 29, no. 3, pp. 394-410, 2007

[7] Colombo C., Del A., and Pala P., Semantics in Visual Information Retrieval, IEEE Multimedia, vol. 6, no. 3, pp. 38-53, 1999.

[8] Daconta C., Obrst J., and Smith T., The Semantic Web: A Guide to Future of XML Web Services and Knowledge Management , Wiley, Indiana, 2003.

[9] Di T., Francesconi M., Frigioni D., and Tarantino L., Tuning CBIR System for Vector Images: The Interface Support, in Proceedings of the Working Conference on Advanced Visual Interfaces , Italy, pp. 425-428, 2004.

[10] Enser B., Sandom J., and Lewis H., Automatic Annotation of Images from the Practitioner Perspective, in Proceedings of the Image and Video Retrieval: 4 th International Conference, Singapore , pp. 497-506, 2005.

[11] Eakins P. and Graham E., Content-Based Image Retrieval: A Report to the JISC Technology Applications Programme, University of Northumbria at Newcastle , Institute for Image Data Research, 2008.

[12] Hearst A., Modern Information Retrieval , Addison Wesley, London, 1999.

[13] Hearst A., TileBars: Visualization of Term Distribution Information in Full Text Information Access, in Proceedings of the Searching and Browsing Text Collections with Large Category Hierarchie, ACM SIGCHI Conference on Human Factors in Computing Systems , Denver, USA, pp. 59-66, 1995.

[14] Herman I. and Dardailler D., SVG Linearization and Accessibility, Computer Graphics Forum , vol. 21, no. 4, pp. 777, 2002.

[15] Hofstede M., Proper A., and Van P., Query Formulation As an Information Retrieval Problem, The Computer Journal , vol. 39, no. 4, pp. 255-274, 1996.

[16] Jaimes A. and Chang F., Image Databases Search and Retrieval of Digital Imagery, John Wiley, New York, pp. 497-565, 2002.

[17] Lovet G. and Dardailler D., SVG Linearizer Tool, W3C Note, /ASVG/ , 2000.

[18] Minsky M., Commonsense-Based Interfaces, Communications of the ACM , vol. 43, no. 8, pp. 66-73, 2000.

[19] Pentland A., Picard W., and Sclaroff S., Photobook: Tools for Content-Based Manipulation of Image Database, International Journal of Computer Vision , vol. 18, no. 3, pp. 233-254, 1996. 122 The International Arab Journal of Inform ation Technology, Vol. 6, No. 2, April 2009

[20] Pun T. and Milanese R., Computer Vision and Multimedia Information Systems, in Proceedings of the International Workshop on Multimedia Information Systems and Hypermedia , Japan, pp. 29-37, 1995.

[21] Smith R. and Chang F., VisualSeek: A Fully Automated Content-Based Image Query System, in Proceedings of the 4 th ACM International Multimedia Conference, India, pp. 87-98, 1996.

[ 2 2 ] Vailaya A., Figueiredo M., Jain K., and Zhang J., Content-Based Hierarchical Classification of Vacation Images, in Proceedings of IEEE International Conference on Multimedia Computing and Systems (ICMCS'99) , vol. 1, no. 1, pp. 518-523, 1999.

[23] Van M. and De P., The Psychology of Multimedia Databases, in Proceedings of the 5 th ACM Conference on Digital Libraries , USA, pp. 1-9, 2000.

[24] Van J., Information Retrieval, 2 nd Edition, Butterworth-Heinemann, London, 1979. Shahrul Noah received his MSc and PhD in information studies from the University of Sheffiled, UK in 1994 and 1998, respectively. His research interests include information retrieval, knowledge representation, and semantic web. He currently leads the knowledge technology research group at the national university of Malaysia. He is a member of the IEEE computer society. Saiful Sabtu received his Bsc of Information Technology degree from the same university. His research interests include information retrieval and multimedia information systems. Binding Semantic to a Sketch Based Query Specification Tool 123 Appendix 1: Example of a duck drawn using the query canvas and its linearization output Duck Image A simple duck image true A duck drawn with polylines A drawing of the duck Title of the query: "Duck Image" A simple duck image Information on #duck A duck drawn with polylines Information on #theDuck A drawing of the duck Raster form Text-based output Real SVG Code