IFSA-EUSFLAT 2009 , 2009-01-23

Title : ( A Hybrid Method for Soccer Video Events Retrieval Using Fuzzy Systems )

Authors: E. Lotfi , Mohammad Reza Akbarzadeh Totonchi , Hamid Reza Pourreza , M. Yaghoubi , F. Dehghan ,

Citation: BibTeX | EndNote

Abstract

Abstract— Most information retrieval systems make indirect use of human knowledge in their retrieval process. The new method we present here aims to efficiently use human knowledge directly in combination with support vector machines for clustering. As illustrated in this paper, this approach is particularly applicable to concept retrieval from soccer-related videos. The first phase consists of extracting suitable features from video shots. Then, using a fuzzy rule base containing the experiences of experts, shots that do not include significant events are removed. Finally, the last phase uses SVM to classify results coming from the fuzzy system. The results of the classification phase are accompanied by a textual description and enables retrieval through text based query. Experimental result show good classification and satisfying retrieval process.

Keywords

, Event Retrieval, Semantic Indexing, Hybrid Method, Fuzzy System, SVM, Soccer Video
برای دانلود از شناسه و رمز عبور پرتال پویا استفاده کنید.

@inproceedings{paperid:1013675,
author = {E. Lotfi and Akbarzadeh Totonchi, Mohammad Reza and Pourreza, Hamid Reza and M. Yaghoubi and F. Dehghan},
title = {A Hybrid Method for Soccer Video Events Retrieval Using Fuzzy Systems},
booktitle = {IFSA-EUSFLAT 2009},
year = {2009},
keywords = {Event Retrieval; Semantic Indexing; Hybrid Method; Fuzzy System; SVM; Soccer Video},
}

[Download]

%0 Conference Proceedings
%T A Hybrid Method for Soccer Video Events Retrieval Using Fuzzy Systems
%A E. Lotfi
%A Akbarzadeh Totonchi, Mohammad Reza
%A Pourreza, Hamid Reza
%A M. Yaghoubi
%A F. Dehghan
%J IFSA-EUSFLAT 2009
%D 2009

[Download]