Live Cloud based dynamic Fuzzy Semantic Relevance Matrix based CBIR

Pawandeep Saini, Hardeep Singh

Abstract


In this paper, a relevance feedback algorithm based fuzzy semantic relevance matrix (FSRM), is constructed to describe the semantically relevance between the images in the database. The weights in the FSRM are adjusted according to user’s feedback in each feedback and the FSRM are modified by learning more time. The algorithm does not need a priori knowledge of specific problem because it based on FSRM. A fuzzy set is a class of objects with a continuum of grades of membership. Fuzzy sets characteristic a set 0, 1 expand to the interval [0, 1]. Therefore, we use the value of interval [0, 1] represents the ”grade of membership” of an object of the concept. The more the value close to 1, the more the object belongs to the concept. The semantic gap between low level visual features and high level semantic concepts is an obstacle to the development of image retrieval. Relevance feedback techniques narrow the semantic gap to some extent. In this paper a relevance feedback algorithm is presented based on fuzzy semantic relevance matrix (FSRM). During the retrieval process, the weights in the FSRM are adjusted according to user’s feedback and the FSRM are modified by learning more time. Experimental results show the effectiveness of the algorithm in the paper.


Keywords: FSRM, CBIR, Color matching, texture matching, relevance feedback.


Full Text:

PDF


DOI: https://doi.org/10.26483/ijarcs.v6i5.2488

Refbacks

  • There are currently no refbacks.




Copyright (c) 2016 International Journal of Advanced Research in Computer Science