Abstract
The motivation for this work is to develop an image retrieval system that can discriminate between images and that can learn user’s preference with feedback to make more intelligent. This paper proposes a neural network to extend prototype refinement which retains information fed by users. The proposed three-layered neural network indexes an image database and makes clusters by an unsupervised approach at a hidden layer. Given a query, the neural system retrieves similar images by computing similarities with images in the near clusters by a supervised approach at an output layer. To provide preference, users can select some images as relevant ones or irrelevant ones. With this feedback, the proposed refinement method estimates global approximations of radial-basis functions centered, and simultaneously adjusts corresponding prototypes. The system demonstrated the effectiveness of prototype refinement generated by the proposed neural network.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cox, I.J., Miller, M.L., Minka, T.P., Yianilos, P.N.: An optimized interaction strategy for Bayesian relevance feedback. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 553-558 (1998)
Haykin, S.: Neural Networks: A Comprehensive Foundation. Macmillan College Publishing Company, New York (1994)
Huang, J., Kumar, S.R., Mitra, M.: Combining supervised learning with color correlograms for content-based image retrieval. In: proceedings of ACM Multimedia, pp. 325–334 (1997)
Lee, K.-M., Street, W.N.: Automated detection, segmentation, classification of breast cancer nuclei: adaptive resource-allocating network. IEEE Transactions on Neural Networks 14(3), 680–687 (2003)
Lee, K.-M., Street, W.N.: Incremental feature weight learning and its application to shape-based query system. Pattern Recognition Letters 23(7), 865–874 (2002)
Li, J., Wang, J.Z.: Automatic linguistic indexing of pictures by a statistical modeling approach. IEEE Transactions on Pattern Analysis and Machine Intelligence (2003)
Maron, O., Ratan, A.L.: Multiple-instance learning for natural scene classification. In: proceedings of the International Conference on Machine Learning, pp. 341–349 (1998)
Minka, T.P., Picard, R.W.: Interactive learning using a “society of models”. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 447–452 (1996)
Nastar, C., Mitschke, M., Meihac, C.: Efficient query refinement for image retrieval. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 547–552 (1998)
Nürnberger, A.: User Adaptive Categorization of Document Collections. In: Nürnberger, A., Detyniecki, M. (eds.) AMR 2003. LNCS, vol. 3094, pp. 95–106. Springer, Heidelberg (2004)
Pass, G., Zabih, R.: Histogram refinement for content. based image retrieval. In: proceesings of the IEEE Workshop on Applications of Computer Vision, pp. 96–102 (1996)
Platt, J.: A resource-allocating network for function interpolation. Neural Computation 3(2), 213–225 (1991)
Rui, Y., Huang, T.S., Mehrotra, S.: Content-based image retrieval with relevance feedback in MARS. In: proceedings of the IEEE International Conference on Image Processing, vol. II, pp. 815–818 (1997)
Wang, J.Z., Li, J., Wiederhold, G.: SIMPLIcity: Semantics-sensitive integrated matching for picture LIbraries. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(9), 47–963 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lee, KM. (2004). Neural Network-Generated Image Retrieval and Refinement. In: Nürnberger, A., Detyniecki, M. (eds) Adaptive Multimedia Retrieval. AMR 2003. Lecture Notes in Computer Science, vol 3094. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-25981-7_14
Download citation
DOI: https://doi.org/10.1007/978-3-540-25981-7_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22163-0
Online ISBN: 978-3-540-25981-7
eBook Packages: Springer Book Archive