 Abstract—In this paper a parameterized geometric alignment method is proposed for minutiae-based fingerprint template protection by transforming an original minutia vicinity into a geometrically-aligned and protected minutia vicinity by randomly generated parameters. Template diversification can be achieved by setting different parameters for different minutiae vicinities. Comparison result of two protected templates is summarized from comparison results of protected minutiae vicinities from both templates. Experimental results on the public FVC2002DB2_A database show satisfactory biometric performance (with average Equal Error Rate 0.0404) of the proposed algorithm. Performance and security analysis are also given for the proposed approach. I. INTRODUCTION ingerprint templates need careful protection because fingerprint characteristics cannot be updated like usual passwords or PIN codes. Standard encryption (DES, AES, etc) is insufficient to protect a biometric template because the encrypted template needs decryption to invert to its plain-text for comparison. This is insecure as full access to samples or unprotected biometric features is given to the potentially untrusted entity that conducts the comparison. It is preferable to run the comparison process in an encrypted domain. However standard encryption algorithms tolerate no fuzzy distortions inherent with fingerprint samples, neither do cryptographic hash functions such as SHA-1, MD5, …,etc., by purpose. Therefore, biometric template protection algorithms [1-21] were proposed, among which fingerprint template protection algorithms were intensively investigated [2,4-6,8-9,13-16,19-20]. Fingerprint template protection algorithms can use different biometric features: luminance features with image processing techniques [4-5]; minutiae features complemented with additional biometric features (such as ridge surroundings) [6,16]; and the only minutiae features based algorithms which protects already-generated minutiae templates conforming to ANSI or ISO standards. However, the key-inversion attack [12] was found towards the fuzzy vault approach [2]. Fuzzy extractor [13] and secure sketch [14] don't suffer from the key-inversion attack, but they sacrifice comparison accuracy. Biotokens [15] exhibits good performance by exploiting enlarged feature  Manuscript received June 7, 2009. This work was supported by funding under the Seventh Research Framework Programme of the European Union, Project TURBINE (ICT-2007-216339). Bian Yang is with the Norwegian Information Security Laboratory at Gjøvik University College, Gjøvik, N-2821, Norway. (phone: +47-61135256; fax: +47-61135170; e-mail: bian.yang@hig.no). Christoph Busch is with the Norwegian Information Security Laboratory at Gjøvik University College, Gjøvik, N-2821, Norway. (phone: +47- 61135194; fax: +47-61135170; e-mail: christoph.busch@hig.no). space, but with large template size which in turn makes this algorithm less attractive to storage-limited applications such as Reference-on-Card systems or On-Card-Comparison systems [22]; in addition, the unprotected information (“control” and “residual” bytes) in [15] might be weak to privacy threats such as linking across different protected templates diversified from the same fingerprint. The method of cancelable fingerprint templates [9] was proposed to distort minutiae data in a non-invertible way. As this mechanism is non-invertible, there is no way to launch the key-inversion attack [12]. All minutiae are assumed to be pre-aligned in [9], but in practical cases a failure-to-align rate of approximately 10% is likely to occur [23]. The pre- alignment accuracy will impact the end-to-end biometric performance. The work [19-20] was also constrained by the same pre-condition of accurate core point detection, which is difficult to achieve in practical applications. We propose a geometric alignment method for each minutia vicinity, which is formed by the minutia itself and its M closest neighboring minutiae. To diversify the original minutia vicinity into various protected vicinities, the geometric alignment is achieved with randomly generated parameters. The geometrically-aligned vicinity can be compared individually and comparisons of all geometrically-aligned vicinities will contribute to a score indicating the similarity of two protected minutiae templates. The proposed parameterized geometric alignment based template protection algorithm is designed to achieve the following goals: • reliable geometric alignment without need of inherent homologous points such as core or delta in the original minutia template; • satisfactory biometric performance; • non-invertibility from a protected template to its original unprotected minutiae template; • unlinkability among diversified protected templates from one fingerprint. The reminder of the paper is structured as follows: Section II presents the proposed method, Section III demonstrates the experimental results, Section IV gives a security analysis, and Section V concludes this paper. II.PROPOSED P ARAMETERIZED GEOMETRIC ALIGNMENT BASED FINGERPRINT MINUTIAE TEMPLATE PROTECTION A. General Framework Fig.1 illustrates a general framework for the proposed parameterized geometric alignment based fingerprint Parameterized Geometric Alignment for Minutiae-Based Fingerprint Template Protection Bian Yang and Christoph Busch F 978-1-4244-5020-6/09/$25.00 ©2009 IEEE