A knowledge-based Decision Support System for adaptive fingerprint identification that uses relevance feedback

In this paper, the use of relevance feedback with fingerprint identification systems is investigated. Two key limitations in current systems are addressed. Firstly, performance in current systems is highly dependent upon the fingerprint features selected for identification and the accuracy of the underlying pattern matching algorithm. Secondly, there is no effective mechanism to improve future queries through knowledge captured from the users, who are often experienced fingerprint examiners. Relevance feedback, a human computer interaction technique to capture and re-use knowledge of a user, has been studied extensively in text-based document retrieval systems and content-based image retrieval systems, but to date examples of its application to fingerprint identification systems are rare. By exploiting relevance feedback, this paper presents a user-centric and adaptive framework that allows tacit knowledge of fingerprint examiners to be captured and re-used to enhance their future decisions. The outcome is a knowledge-based Decision Support System (DSS) that provides the examiner with both intuitive visualization displays to analyze the relationships between images in the fingerprint database and relevance feedback facility to produce a persistent and personalized semantic space overlay. This serves a long term memory that can be updated to reflect the knowledge captured from the user. Empirical experiments confirmed the ability of this approach to improve the accuracy of fingerprint identification queries when compared to the static data processing architecture of current systems.