Combined Retrieval Strategies for Images with and without Distinct Objects

  • Hong Fu
  • Zheru Chi
  • Dagan Feng
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6474)


This paper presents the design of an all-season image retrieval system. The system handles the images with and without distinct object(s) using different retrieval strategies. Firstly, based on the visual contrasts and spatial information of an image, a neural network is trained to pre-classify an image as distinct-object or no-distinct-object category by using the Back Propagation Through Structure (BPTS) algorithm. In the second step, an image with distinct object(s) is processed by an attention-driven retrieval strategy emphasizing distinct objects. On the other hand, an image without distinct object(s) (e.g., a scenery images) is processed by a fusing-all retrieval strategy. An improved performance can be obtained by using this combined approach.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fu, H., Chi, Z., Feng, D.: Attention-Driven Image Interpretation with Application to Image Retrieval. Pattern Recognition 39(9), 1604–1621 (2006)CrossRefzbMATHGoogle Scholar
  2. 2.
    Fu, H., Chi, Z., Feng, D.: An Efficient Algorithm for Attention-Driven Image Interpretation from Segments. Pattern Recognition 42(1), 126–140 (2009)CrossRefzbMATHGoogle Scholar
  3. 3.
    Vu, K., Hua, K.A., Tavanapong, W.: Image Retrieval Based on Regions of Interest. IEEE Transactions on Knowledge and Data Engineering 15(4), 1045–1049 (2003)CrossRefGoogle Scholar
  4. 4.
    Tian, Q., Wu, Y., Huang, T.S.: Combine User Defined Region-Of-Interest and Spatial Layout for Image Retrieval. In: IEEE International Conference on Image Processing, vol. 3, pp. 746–749 (2000)Google Scholar
  5. 5.
    Zhang, J., Yoo, C.W., Ha, S.W.: ROI Based Natural Image Retrieval Using Color and Texture Feature. In: Proceedings - Fourth International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2007, vol. 4, art. no. 4406479, pp. 740–744 (2007)Google Scholar
  6. 6.
    Zhang, Q., Izquierdo, E.: Adaptive Salient Block-Based Image Retrieval in Multi-Feature Space. Signal Processing: Image Communication 22(6), 591–603 (2007)Google Scholar
  7. 7.
    Hare, J.S., Lewis, P.H.: Salient Regions for Query by Image Content. In: Enser, P.G.B., Kompatsiaris, Y., O’Connor, N.E., Smeaton, A., Smeulders, A.W.M. (eds.) CIVR 2004. LNCS, vol. 3115, pp. 317–325. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  8. 8.
    Guan, J., Qiu, G.: Modeling User Feedback Using a Hierarchical Graphical Model for Interactive Image Retrieval. In: Ip, H.H.-S., Au, O.C., Leung, H., Sun, M.-T., Ma, W.-Y., Hu, S.-M. (eds.) PCM 2007. LNCS (LNAI), vol. 4810, pp. 18–29. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  9. 9.
    Golloer, G., Kuchler, A.: Learning Task-Dependent Distributed Representations by Backpropagation through Structure. In: IEEE International Conferences on Neural Networks, pp. 347–352 (1996)Google Scholar
  10. 10.
    Cho, S.Y., Chi, Z.: Genetic Evolution Processing of Data Structures for Image Classification. IEEE Transactions on Knowledge and Data Engineering 17(2), 216–231 (2005)CrossRefGoogle Scholar
  11. 11.
    Cho, S.Y., Chi, Z., Wang, Z., Siu, W.C.: An efficient learning algorithm for adaptive processing of data structure. Neural Processing letter 17(2), 175–190 (2003)CrossRefzbMATHGoogle Scholar
  12. 12.
    Fu, H., Chi, Z., Feng, D., Zou, W., Lo, K., Zhao, X.: Pre-classification module for an all-season image retrieval system. In: Proceedings of International Joint Conference on Neural Networks, Orlando, Florida, USA, paper 1688, 5 pages (August 12-17, 2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Hong Fu
    • 1
    • 2
  • Zheru Chi
    • 1
  • Dagan Feng
    • 1
    • 3
  1. 1.Department of Electronic and Information EngineeringThe Hong Kong Polytechnic UniversityHong Kong
  2. 2.Department of Computer ScienceChu Hai College of Higher EducationHong Kong
  3. 3.School of Information TechnologiesThe University of SydneyAustralia

Personalised recommendations