Fuzzy generalized median graphs computation: Application to content-based document retrieval. (December 2017)

• Record Type: Journal Article
• Authors: Chaieb, Ramzi; Kalti, Karim; Luqman, Muhammad Muzzamil; Coustaty, Mickaël; Ogier, Jean-Marc; Essoukri Ben Amara, Najoua
• Is Part Of: Pattern recognition. Volume 72(2017:Dec.)
• Page Start: 266
• Page End: 284
• Publication Date: 2017-12
• Subjects: Fuzzy attributed relational graph -- Graph embedding -- Fuzzy set median graph -- Fuzzy generalized median graph -- Similarity measure -- Document image retrieval; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2017.07.030
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We propose a new algorithm for the computation of the Fuzzy Generalized Median Graph (FGMG). We applied the proposed algorithm to the Content-based Document Retrieval (CBDR) problem. Query and database document images are represented by Fuzzy Attributed Relational Graphs (FARGs). We propose a new FARG embedding method in order to reduce the computation time of the FGMG. Our algorithm improves the accuracy and speed of document image retrieval processing. Abstract: Fuzzy median graph is an important new concept that can represent a set of fuzzy graphs by a representative fuzzy graph prototype. However, the computation of a fuzzy median graph remains a computationally expensive task. In this paper, we propose a new approximate algorithm for the computation of the Fuzzy Generalized Median Graph (FGMG) based on Fuzzy Attributed Relational Graph (FARG) embedding in a suitable vector space in order to capture the maximum information in graphs and to improve the accuracy and speed of document image retrieval processing. In this study, we focus on the application of FGMGs to the Content-based Document Retrieval (CBDR) problem. Experiments on real and synthetic databases containing a large number of FARGs with large sizes show that a CBDR using the FGMG as a dataset representative yields better results than an exhaustive and sequential retrieval in terms of gains in accuracy and time processing.