Applying Neural Network to Combining the Heterogeneous Features

Abstract

The content of an image can be shown in terms of different characteristics such as color, texture, shape, or text annotations. Retrieval based on these features can be various by the way how to combine the feature values. Various types of database systems are currently in use today, these information resources could be immediately made available for many users through existing computer systems However, since these systems often use different data models and different query languages users of one system cannot easily access the data stored in other systems. There is a growing need for tools to maximize the reusability and interoperability of arbitrary computing services while keeping the autonomy of pre-existing databases in federated approach. The global of a multidatabase system is schema exported from the underlying databases. One way of achieving interoperability among heterogeneous and autonomous database management systems is to develop a multi database system which supports a single common data model and a single query language on top of different types of existing systems. In this paper, A Feedforword Neural Network has been introduced to integrates three Heterogeneous multidatabases with the same model relational but different software environments and present a procedure using a classifier to categorize attributes according to their field, specifications and data values. Then train a neural network to recognize attributes different sites.