A high-dimensional indexing scheme for scalable fingerprint-based identification
This paper describes an application of the Flash algorithm  to scalable fingerprint-based identification (one-to-many searches). Flash is a high-dimensional indexing algorithm akin to Geometric Hashing  that has been used for similarity searching in a number of other domains, including model based object recognition , genomic sequences homology detection , and 3D flexible molecular matching and docking .
A large number of independent properties of each model fingerprint that are invariant under Euclidean transformations are extracted and stored in a look-up table. Match candidates and their pose transformation parameters are then formed by indexing in this table, using identical invariants generated from a query fingerprint. This has the desirable properties of determining appropriate match candidates without having to compare the query to each individual model fingerprint in the database. Candidate hypothesis evidence is then gathered in a parameter space with an approach similar to the Generalized Hough Transform .
Results of this preliminary implementation on a database of 100,000 models show good scalability properties. Measured False Positive and False Negative Rates allow this approach to be extended to databases with tens of millions of fingerprints. Reported performance measurements show an equivalent 1 to 1 matching rate of about 150,000 prints/sec. on an 8-way SMP PowerPC workstation or, equivalently, on an 8-node SP/2 platform.
KeywordsFalse Positive Rate False Negative Rate Combinatorial Index Identical Invariant Euclidean Transformation
Unable to display preview. Download preview PDF.
- ANSI/IAI, “Automated fingerprint identification systems-benchmark tests of relative performance.” Technical Report ANSI/IAI 1-1988, American National Standards Institute, 1988.Google Scholar
- D.H. Ballard, “Generalizing the Hough transform to detect arbitrary shapes,” Pattern Recognition, Vol. 13, No. 2, 1981, pp. 111–122.Google Scholar
- A. Califano and R. Mohan, “Multidimensional indexing for Recognizing Visual Shapes.” IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(4):373–392, April 1994. Also, U.S. Patent Number 5,351,3 10, September 1994Google Scholar
- A.Califano, I.Rigoutsos: “FLASH: A Fast Look-up Algorithm for String Homology,” of IEEE Conf. on Computer Vision and Pattern Recognition 1993, New York.Google Scholar
- C.J. Date, “An Introduction to Database Systems.” Addison-Wesley, 1995.Google Scholar
- J.G. Daugman, “High Confidence Visual Recognition of Persons by a Test of Statistical Independence.” IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(11):1148–1161,1993.Google Scholar
- W.E.L. Grimson, “The combinatorics of heuristic search termination for object recognition in cluttered environments,” MIT AI Memo 1111, MIT, May 1989.Google Scholar
- R.M. Haralick, H. Joo, C. Lee, X. Zhuang, V.G. Vaidya, and M.B. Kim, “Pose Estimation from Corresponding Point Data.” IEEE Transactions on Systems, Man, and Cybernetics, 19(6):1426–1446, 1989.Google Scholar
- D.P. Huttenlocher and S. Ulmann, “Object Recognition Using Alignment.” In Proceedings of the First International Conference on Computer Vision, pp. 102–111. IEEE Computer Society Press, 1987.Google Scholar
- A. Jain, L. Hong, S. Pankanti, and R. Bolle. An Identity Authentication System Using Fingerprints. Proceedings of the IEEE, 85(9):1365, September 1997.Google Scholar
- Y. Lamdan and H.J. Wolfson, “Geometric Hashing: A General and Efficient Model-based Recognition Scheme.” In Proceedings of the Second International Conference on Computer Vision, pp. 238–249, 1988.Google Scholar
- H.C. Lee and R.E. Gaensslen, editors. Advances in Fingerprint Technology, CRC Press, 1994.Google Scholar
- E.L. Lehmann, “Testing Statistical Hypotheses.” Second Edition. Springer-Verlag, 1986.Google Scholar
- J.Neyman and E.S. Pearson. “On the Problem of the Most Efficient Tests of Statistical Hypotheses.” Philosopical Transactions of the Royal Society of London, 231A:289, 1933.Google Scholar
- N.K. Ratha, K. Karu, S. Chen, and A.K. Jain. “A Real-Time Matching System for Large Fingerprint Databases.” IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(8):799–813, August 1996.Google Scholar
- I.Rigoutsos, D.Platt, A.Califano: “Flexible 3D-Substructure Matching & Novel Conformer Derivation in Very Large Databases of 3D Molecular Information,” to be published in Journal of Computer-Aided Molecular Design.Google Scholar
- M.K. Sparrow. “Measuring AFIS Matcher Accuracy.” The Police Chief, pp. 147–151, April 1994.Google Scholar
- G. Stockman, “Object Recognition and Localization Via Pose Clustering.” Computer Vision, Graphics, and Image Processing, 40:361–387, 1987.Google Scholar
- B. Stroustrup, “The C++ Programming Language, Third Edition.” Addison-Wesley, 1997.Google Scholar
- J.D. Ullman and J. Widom. “A First Course in Database Systems.” Prentice Hall, 1997.Google Scholar