Indexing of Large Biometric Database

Abstract

The word "biometrics" is derived from the Greek words 'bios' and 'metric' which means life and measurement respectively. This directly translates into "life measurement". Biometrics is the automated recognition of individuals based on their behavioral and biological characteristics. Biometric features are information extracted from biometric samples which can be used for comparison with a biometric reference. Biometrics comprises methods for uniquely recognizing humans based upon one or more intrinsic physical or behavioral traits. In computer science, in particular, biometrics is used as a form of identity access management and access control. It is also used to identify individuals in groups that are under surveillance. Biometrics has fast emerged as a promising technology for authentication and has already found place in most hi-tech security areas. An efficient clustering technique has been proposed for partitioning large biometric database during identification. The system has been tested using bin-miss rate as a performance parameter. As we are still getting a higher bin-miss rate, so this work is based on devising an indexing strategy for identification of large biometric database and with greater accuracy. This technique is based on the modified B+ tree which reduces the disk accesses. It decreases the data retrieval time and also possible error rates. The indexing technique is used to declare a person’s identity with lesser number of comparisons rather than searching the entire database. The response time deteriorates, as well as the accuracy of the system degrades as the size of the database increases. Hence for larger applications, the need to reduce the database to a smaller fraction arises to achieve both higher speeds and improved accuracy. The main purpose of indexing is to retrieve a small portion of the database for searching the query. Since applying some traditional clustering schemes does not yield satisfactory results, we go for an indexing strategy based on tree data structures. Index is used to look-up, input and delete data in an ordered manner. Speed and efficiency are the main goals in the different types of indexing. Speed and efficiency include factors like access time, insertion time, deletion time, and space overhead. The main aim is to perform indexing of a database using different trees beginning with Binary Search tree followed by B tree before proceeding to its variations, B+ tree and Modified B+ tree, and subsequently determine their performance based on their respective execution times.