Rough Texton based Fundus Image Retrieval

Abstract

Content based image retrieval (CBIR), is a robust technique widely used in the field of image retrieval. This method uses visual contents like color, texture and shape, to search images from a large scale database of images. Among the primary image contents, texture is an important spatial feature. Texton is a statistical approach used to analyze the texture of an image. Texture-based approach proposed here can take into account the vagueness of images also while retrieving images just as an expert manually retrieves medical images.