Description

In this paper, we describe about content Based Image retrieval (CBIR). This employs to identify the abnormality in the retinal Images. To achieve this goal, we describe a framework that aggregates and extracts features and classify about the Retinal. This paper highlights the challenges and potential applications of finding abnormality to improve the access, integration, and interpretation of clinical patient data. We extracting GLCM feature for the image. In the GLCMs, several statistics information is derived using the different formulas. These statistics provide information about the texture of an image. Such as Energy, Entropy, Dissimilarity, Contrast, Inverse difference, correlation Homogeneity, Auto correlation, Cluster Shade Cluster Prominence, Maximum probability, Sum of Squares will be calculated for texture image. SFSKNN is the combination of Sequential feature selection (SFS) and k-nearest neighbor (KNN). The extracted GLCM features are input to the feature selection process. Regression tree classification will classify the feature in tree structure. It will select splits for features. After classifying it will predict the abnormality of the image.