Fisher Linear Discriminant Analysis for text-image combination in multimedia information retrieval

PATTERN RECOGNITION

卷:47

Article

Moulin, Christophe¹  Largeron, Christine¹  Ducottet, Christophe¹  Gery, Mathias¹  Barat, Cecile¹ 

[1] Univ St Etienne, CNRS, Lab Hubert Curien, Univ Lyon,UMR 5516, F-42000 St Etienne, France

关键词: Multimedia information retrieval;    Textual and visual information;    Bag-of-words;    Parameters learning;    Fischer LDA;   

DOI  :  10.1016/j.patcog.2013.06.003

来源: Elsevier

【 摘 要 】

With multimedia information retrieval, combining different modalities - text, image, audio or video provides additional information and generally improves the overall system performance. For this purpose, the linear combination method is presented as simple, flexible and effective. However, it requires to choose the weight assigned to each modality. This issue is still an open problem and is addressed in this paper. Our approach, based on Fisher Linear Discriminant Analysis, aims to learn these weights for multimedia documents composed of text and images. Text and images are both represented with the classical bag-of-words model. Our method was tested over the ImageCLEF datasets 2008 and 2009. Results demonstrate that our combination approach not only outperforms the use of the single textual modality but provides a nearly optimal learning of the weights with an efficient computation. Moreover, it is pointed out that the method allows to combine more than two modalities without increasing the complexity and thus the computing time. (C) 2013 Elsevier Ltd. All rights reserved.

【 授权许可】

Free