VSE knjižnice (vzajemna bibliografsko-kataložna baza podatkov COBIB.SI)
  • A hybrid image retrieval system with user's relevance feedback using neurocomputing
    Wang, Dianhui ; Ma, Xiaohang
    This paper aims at developing a hybrid scheme for intelligent image retrieval using neural nets. Each item in an image database is indexed by a visual feature vector, which is extracted using color ... moments and descrete cosine transform coefficients. Query is characterizated by a set of semantic labels, which are predefined by system designers and associated with domain concerns. The proposed hibrid image retrieval (HIR) system utilizers the image content feature as the system input, and the semantic labels as its output. To compensate the deficiency of semantics modelling, an on-line user's relevance feedback is applied to improve the retrieval performance of the HIR system. The neural net acts like a pattern association memory bank that maps the low-level feature to their corrensponding semantic labels. During the retrieval process, the weights of the neural net are updated by an interactive user's relevance feedback technique, where the feedback signal comprise the neural net actual output, semantic labels provided by users and the given query. A prototype HIR is implemented and evaluated usng an artificial image database. Experimental results demonstrate that our proposed techniques are promising.
    Vir: Informatica : an international journal of computing and informatics. - ISSN 0350-5596 (no. 3, 2005, str. 271-279)
    Vrsta gradiva - članek, sestavni del
    Leto - 2005
    Jezik - angleški
    COBISS.SI-ID - 19428903

Vnos na polico