Curvature Signature Based Image Retrieval System

Abstract

Shape is one of the chief low level image description in Content Based Image Retrieval (CBIR).Image is a key reason in several areas. The more functional the images are being stored,the more capable the images are important for those regions to be able to regain the stored image quickly and be retrieve later,this is where content-Based Image Retrieval(CBIR) move towards in.Content Based Image Retrieval(CBIR) is a technique used for regaining similar images for given input image from an image database. CBIR aims to recover the images based on the content of a given image rather than textual data of a file name. CBIR uses the various features such as color, texture, shape etc. The shape is free of transformations like scaling, translation, rotation and flip. A good shape representation method repossess similar images irrespective of the transformation performed on a shape. Curvature is a very significant boundary feature for human to critic relationship between shapes. Even though curvature is important curve feature, there is a difficulty for using curvature as shape representation.Inorder to overcome the difficulty smooth curve function is being derived. This helps you to show the curvature signatures of a particular shape.