2013 | OriginalPaper | Buchkapitel
Content-Based Diversifying Leaf Image Retrieval
verfasst von : Sheng-Ping Zhu, Ji-Xiang Du, Chuan-Min Zhai
Erschienen in: Intelligent Computing Theories and Technology
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
In recent years, content-based image retrieval achieved continuous development, the main goal so far has been to retrieve similar objects for a given query, and only the relevance is cared in retrieval system, so many duplicate or near duplicate documents retrieved in response to a query. For efficient content-based image retrieval, we propose the Content-based Diversifying Leaf Image Retrieval in this paper. In order to make the retrieval results have relevance and diversity, we extract leaf image feature and use the relevance feedback technique based of SVM and the AP clustering algorithm. We also proposed a new evaluation function - Maximal Scatter Diversity (MSD) static evaluation function. Experimental results show that our approach can achieve good performance with improving the diversity of the retrieval results without reduction of their relevance.