Probabilistic image retrieval approaches can lead to significant gains over standard retrieval techniques. However, this occurs at the cost of a significant increase in computational complexity. In fact, closed-form solutions for probabilistic retrieval are currently available only for simple representations such as the Gaussian and the histogram. We analyze the case of mixture densities and exploit the asymptotic equivalence between likelihood and Kullback-Leibler divergence to derive solutions for these models. In particular, (1) we show that the divergence can be computed exactly for vector quantizers and, (2) has an approximate solution for Gaussian mixtures that introduces no significant degradation of the resulting similarity judgments. In both cases, the new solutions have closed-form and computational complexity equivalent to that of standard retrieval approaches, but significantly better retrieval performance.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    On the complexity of probabilistic image retrieval


    Contributors:


    Publication date :

    2001-01-01


    Size :

    767363 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    On the Complexity of Probabilistic Image Retrieval

    Vasconcelos, N. / IEEE | British Library Conference Proceedings | 2001


    Medical image retrieval based on complexity analysis

    Backes, A. R. / Bruno, O. M. | British Library Online Contents | 2010


    A probabilistic semantic model for image annotation and multimodal image retrieval

    Ruofei Zhang, / Zhongfei Zhang, / Mingjing Li, et al. | IEEE | 2005


    Probabilistic Feature Relevance Learning for Content-Based Image Retrieval

    Peng, J. / Bhanu, B. / Qing, S. | British Library Online Contents | 1999


    A Probabilistic Semantic Model for Image Annotation and Multi-Modal Image Retrieval

    Zhang, R. / Zhang, Z. / Li, M. et al. | British Library Conference Proceedings | 2005