CBIR Feature Extraction Using Neuro-Fuzzy Approach

Abstract

This paper proposes a neuro-fuzzy based CBIR framework for image retrieval. Here, in the first phase, the fuzzy clustering algorithm is used for the classification of the images on the basis of their texture feature. In second phase, result of first phase serves as an input to the back propagation algorithm which helps to find images most semantically related to the query images. Our experiment shows that the proposed method results in better performance in terms of precision and recall as compared to the traditional CBIR techniques.