An efficient region based image retrieval using fuzzy c means algorithm and user interactive multi threshold robust features vector

Abstract

In image processing browsing searching and retrieving images from a large digital image database are carried out using some image mining methods The image mining can be performed over the annotation words In image mining the manual image annotation is time consuming difficult and expensive To address this issue a large number of researches have been completed on automatic image annotation Content based image mining CBIR is one of the image mining methods which use the visual contents to search images from large image databases It is based on visual features such as color and texture CBIR needs manual annotation of every image which is difficult in large image databases Searching image databases using textual annotation which is also language dependent insufficient and ambiguous Sometimes it does not sustain the method of CBIR is not sustainable To overcome these issues following methods are proposed RBIM with SVM classification and Fuzzy C Means Clustering Algorithm Multi focus Fused Image Work Hybrid Hash Laplacian Pyramid A Multi Threshold Scheme for Region Based Image Mining newline