Fuzzy Based Grey Wolf Optimization for Effective Medical Image Retrieval System

In the present digital world, an image databases are increasing enormously across the world. An effective image retrieval approach is needed for utilizing these massive databases. An extensive research effort has been conducted in Content Based Medical Image Retrieval (CBMIR) system. In this contribution, CBMIR system is proposed by extracting the image texture features, selection of best features, classification of best features and to identify the similarity among the images. The selected feature is Local Binary Patterns (LBP) where all the extracted features are saved as a feature database. To reduce the high dimensional texture features, Fuzzy based Grey Wolf Optimization (FGWO) is used to select the best features. Classification algorithm is used as an evaluation criterion, for identifying the best subset of features. Fuzzy based Relevance Vector Machine (FRVM) is used to classify the subset of texture features of the images. Euclidean Distance (ED) is used to identify the similarity between the query image and database of images. To evaluate the proposed CBMIR system, accuracy, precision and recall is used as a performance metrics.