An image retrieval system adaptable to user's interests by the use of relevance feedback via genetic algorithm

ABSTRACT

The emergence of multimedia technology and the rapid expansion of image sets on the internet have attracted a lot of research tools for effective retrieval of visual data. When working in the image retrieval context the main goal is to retrieve images which might be useful or relevant to the user based on features automatically extracted from the images. The proposal of this work is to integrate the information provided by the user into the decision procedure by the use of the relevance feedback mechanism. The relevance feedback technique used is based on genetic algorithms using a proposed order-based fitness function in order to adapt the user's image similarity criteria. Image similarity is expressed as a weighted integration of color, shape and texture features. The retrieval process itself is based on the Local Similarity Pattern, where the image areas are uniformly partitioned into regions, and the similarity between the images is measured by corresponding region similarities. The use of negative and positive weights for the features, into the genetic algorithm, allows one to express, in a continuous way, the concepts of relevance, irrelevance and undesirability in the similarity model used. Experiments in a database with 12750 images has shown that the integration of features through the proposed genetic algorithm into a relevance feedback mechanism provides good results in the image retrieval context.

REFERENCES

• 1: Massachusetts Institute of Technology, Media Laboratory, Vision Texture Database. Available: ftp://whitechapel.media.mit.edu/pub/VisTex/.
• 2: University of Southern California, Signal and Image Processing Institute, The USC-SIPI Image Database, 2001. Available: http://sipi.usc.edu/services/database/-Databases.html.
• 3: Corel Corporation, Corel Gallery 3.0. in James Z. Wang's Research Group. Available: http://wang.ist.psu.edu/~jwang/test1.tar.
• 4: Ricardo A. Baeza-Yates , Berthier Ribeiro-Neto, Modern Information Retrieval, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1999
• 5: S. Brandt. Use of shape features in content-based image retrieval. Master's thesis in science, Helsinki University of Technology, Department of Engineering Physics e Mathematics, Espoo, Finland, 1999.
• 6: D. Y. M. Chan and I. King. Weight assignment in dissimilarity function for chinese cursive script character image retrieval using genetic algorithm. Proceedings of the 4th International Workshop on Information Retrieval with Asian Languages, IRAL'99, Taipei, Taiwan.
• 7: G. Ciocca , R. Schettini, A relevance feedback mechanism for content-based image retrieval, Information Processing and Management: an International Journal, v.35 n.5, p.605-632, Sept. 1999 [doi>10.1016/S0306-4573(99)00021-7]
• 8: M. Crucianu, M. Ferecatu, and N. Boujemaa. Relevance feedback for image retrieval: a short survey. Le Chesnay Cedex, October 2004. France, Italy.
• 9: C. Darwin. The origin of species. ElecBook, London, England, edition based on the text of first edition of 1859 edition, 1997.
• 10: David E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1989
• 11: Randy L. Haupt , Sue Ellen Haupt, Practical Genetic Algorithms with CD-ROM, Wiley-Interscience, 2004
• 12: John H. Holland, Adaptation in natural and artificial systems, MIT Press, Cambridge, MA, 1992
• 13: J. Laaksonen, E. Oja, and M. Koskela. Analyzing low-level visual features using content-based image retrieval. Proceedings of the 7th International Conference on Neural Information Processing, 2000. Teajon, Korea.
• 14: Cristina López-Pujalte , Vicente P. Guerrero-Bote , Félix de Moya-Anegón, Order-based fitness functions for genetic algorithms applied to relevance feedback, Journal of the American Society for Information Science and Technology, v.54 n.2, p.152-160, January 2003 [doi>10.1002/asi.10179]
• 15: G. Salton and C. Buckley. Improving retrieval performance by relevance feedback. Journal of the American Society for Information Science, 41(4):288--297, 1990.
• 16: Z. Stejić, Y. Takama, and K. Hirota. Genetic algorithms for a family of image similarity models incorporated in the relevance feedback mechanism. Applied Soft Computing, 2:306--327, 2003.
• 17: Z. Stejić, Y. Takama, and K. Hirota. Modified hierarquical genetic algorithm for relevance feedback in image retrieval. Intelligent Data Analysis, 8:363--384, 2004.
• 18: Zoran Stejić , Yasufumi Takama , Kaoru Hirota, Mathematical aggregation operators in image retrieval: effect on retrieval performance and role in relevance feedback, Signal Processing, v.85 n.2, p.297-324, February 2005 [doi>10.1016/j.sigpro.2004.10.003]
• 19: M. Stricker and M. Orengo. Similarity of color images. Proceedings of IS&T and SPIE Storage and Retrieval of Image and Video Databases III, 2005. San Jose, United States.
• 20: James Z. Wang , Jia Li , Gio Wiederhold, SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture LIbraries, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.23 n.9, p.947-963, September 2001 [doi>10.1109/34.955109]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Retrieval models

Additional Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.8 Database applications
          Subjects: Image databases
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Relevance feedback
      H.3.4 Systems and Software
          Subjects: User profiles and alert services

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.8 Problem Solving, Control Methods, and Search
          Subjects: Heuristic methods

General Terms:
Algorithms, Design, Management

Keywords:
genetic algorithm, image retrieval, relevance feedback