JACIII Vol.11 No.3 pp. 294-300
doi: 10.20965/jaciii.2007.p0294


Abstract Image Generation Based on Local Similarity Pattern

Yasufumi Takama and Keisuke Shigemori

Tokyo Metropolitan University, 6-6 Asahigaoka, Hino, Tokyo 191-0065, Japan

April 10, 2006
July 28, 2006
March 20, 2007
image retrieval, local similarity pattern (LSP), image processing

The method for generating abstract images from a set of images is proposed. The method selects a representative image from a given set of images, in which the common features in terms of the composition are highlighted with image processing techniques. Common features are extracted based on Local Similarity Pattern (LSP), which has been originally proposed for image retrieval. The selection of representative images is performed based on the difference between the color histogram calculated from a set of regions, of which color features are common, and that calculated from the remaining regions. The experimental results show the performance of the proposed method, in terms of its effectiveness for image classification, as well as the accuracy of selecting representative images. The concept of abstract images is expected to be useful for developing a directory service for searching images on the Web.

Cite this article as:
Yasufumi Takama and Keisuke Shigemori, “Abstract Image Generation Based on Local Similarity Pattern,” J. Adv. Comput. Intell. Intell. Inform., Vol.11, No.3, pp. 294-300, 2007.
Data files:
  1. [1] M. Flicner, H. Sawhney, and W. Niblack, “Query by Image and Video Content: The QBIC System,” IEEE Computer, Vol.28, No.9, pp. 23-32, 1995.
  2. [2] Google Image Search, .
  3. [3] H. Nanba and M. Okumura, “The State of the Art of Automatic Text Summarization,” IPSJ Magazine, Vol.43, No.12, pp. 1287-1294, 2002 (in Japanese).
  4. [4] Open Directory Project,
  5. [5] N. Sagara, W. Sunayama, and M. Yachida, “Image Labeling Using Key Sentences of HTML,” Transaction of the Institute of Electronics, Information and Communication Engineers D-I, Vol.J87-D-I, No.2, pp. 145-153, 2004 (in Japanese).
  6. [6] K. Shigemori, Z. Stejic, K. Hirota, T. Yamaguchi, and Y. Takama, “Proposal of the Site-wise Abstract Image for the Web Image Resource Mining,” ISIS2003, pp. 150-153, 2003.
  7. [7] M. Shishibori et al., “Development of a WWW Image Retrieval System Using the Image Knowledge Database,” Transaction of the Institute of Electronics, Information and Communication Engineers D-I, Vol.J87-D-I, No.2, pp. 154-163, 2004 (in Japanese).
  8. [8] Z. Stejic, Y. Takama, and K. Hirota, “Weighted Local Similarity Pattern as image similarity model incorporated in GA-based relevance feedback mechanism,” Intelligent Data Analysis, Vol.7, No.5, pp. 443-467, 2003.
  9. [9] Z. Stejic, Y. Takama, and K. Hirota, “Genetic algorithms for a family of image similarity models incorporated in the relevance feedback mechanism,” Applied Soft Computing, Vol.2, No.4, pp. 306-327, 2003.
  10. [10] Z. Stejic, Y. Takama, and K. Hirota, “Relevance Feedback-Based Image Retrieval Interface Incorporating Region and Feature Saliency Patterns as Visualizable Image Similarity Criteria,” IEEE Transaction on Industrial Electronics, Vol.50, No.5, pp. 839-852, 2003.
  11. [11] Z. Stejic, Y. Takama, and K. Hirota, “Genetic algorithm-based relevance feedback for image retrieval using local similarity patterns,” Information Processing & Management, Vol.39, pp. 1-23, 2003.
  12. [12] Z. Stejic, Y. Takama, and K. Hirota, “Modified Hierarchical Genetic Algorithm for Relevance Feedback in Image Retrieval,” Intelligent Data Analysis, Vol.8, No.4, pp. 363-384, 2004.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Feb. 25, 2021