It is desirable to impose proper constraints while designing a database, in order to provide efficient information storage and retrieval methods. Identifying and applying the key dependencies on the database is one of the essential features of database design (Date, 1996; and Silbreschatz et al., 1997). While designing a database, there is a possibility that certain dependencies are overlooked. Further, there may be a number of key dependencies, which may not be known at the time of database design, and that affects the efficiency of a Database Management System (DBMS). Hence, it is a general practice to consider expert views while identifying functional dependencies. Extraction of functional dependencies is the fundamental activity in the database design recovery process, which is a part of an overall system reverse engineering effort.

As the number of attributes in a database increases, the number of inherent dependencies is also likely to increase. Identification of all the functional dependencies is a complicated process. The axioms proposed by Armstrong will produce a canonical cover for a given set of functional dependencies and vice versa. This canonical cover will ensure the validity of all the functional dependencies of the given instance. To find all the functional dependencies, a new algorithm is proposed in `Val methodology' (Kumar and Rao, 1999). So far, no research has been done towards finding canonical cover directly without finding functional dependencies.

In this paper, a method is proposed to discover knowledge from binary databases, which is considered as one of the canonical covers of functional dependencies of that instance. Because of the complexity of the general databases, the present work is confined to binary databases, which may not be a constraint, as any general database can be converted into a binary database.

Projective Geometry Tool for Canonical Cover, database, functional, canonical, binary, design, number, instance, constraint, algorithm, Armstrong, attributes, desirable, axioms, engineering, Extraction, fundamental, Identification, information, knowledge, methodology', complexity, complicated, recovery, Silbreschatz