Yuliang He

Image enhancement and minutiae matching in fingerprint verification

Fingerprint image enhancement and minutiae matching are two key steps in an automatic fingerprint identification system. In this paper, we develop a fingerprint image enhancement algorithm based on orientation fields; According to the principles of Jain et al.s matching algorithm, we also introduce ideas along the following three aspects: introduction of ridge information into the minutiae matching process in a simple but effective way, which solves the problem of reference point pair selection with low computational cost; use of a variable sized bounding box to make our algorithm more robust to non-linear deformation between fingerprint images; use of a simpler alignment method in our algorithm. Experiments using the Fingerprint Verification Competition 2000 (FVC2000) databases with the FVC2000 performance evaluation show that these ideas are effective.

Fingerprint matching based on global comprehensive similarity

This paper introduces a novel algorithm based on global comprehensive similarity with three steps. To describe the Euclidean space-based relative features among minutiae, we first build a minutia-simplex that contains a pair of minutiae as well as their associated textures, with its transformation-variant and invariant relative features employed for the comprehensive similarity measurement and parameter estimation, respectively. By the second step, we use the ridge-based nearest neighborhood among minutiae to represent the ridge-based relative features among minutiae. With these ridge-based relative features, minutiae are grouped according to their affinity with a ridge. The Euclidean space-based and ridge-based relative features among minutiae reinforce each other in the representation of a fingerprint. Finally, we model the relationship between transformation and the comprehensive similarity between two fingerprints in terms of histogram for initial parameter estimation. Through these steps, our experiment shows that the method mentioned above is both effective and suitable for limited memory AFIS owing to its less than 1k byte template size.

Modeling and Analysis of Local Comprehensive Minutia Relation for Fingerprint Matching

This paper introduces a robust fingerprint matching scheme based on the comprehensive minutia and the binary relation between minutiae. In the method, a fingerprint is represented as a graph, of which the comprehensive minutiae act as the vertex set and the local binary minutia relations provide the edge set. Then, the transformation-invariant and transformation-variant features are extracted from the binary relation. The transformation-invariant features are suitable to estimate the local matching probability, whereas the transformation-variant features are used to model the fingerprint rotation transformation with the adaptive Parzen window. Finally, the fingerprint matching is conducted with the variable bounded box method and iterative strategy. The experiments demonstrate that the proposed scheme is effective and robust in fingerprint alignment and matching.

Maximum-likelihood deformation analysis of different-sized fingerprints

This paper introduces a probabilistic formulation in terms of Maximum-likelihood estimation to calculate the optimal deformation parameters, such as scale, rotation and translation, between a pair of fingerprints acquired by different image capturers from the same finger. This uncertainty estimation technique allows parameter selection to be performed by choosing parameters that minimize the deformations uncertainty and maximize the global similarity between the pair of fingerprints. In addition, we use a multi-resolution search strategy to calculate the optimal deformation parameters in the space of possible deformation parameters. We apply the method to fingerprint matching in a pension fund management system in China, a fingerprint-based personal identification application system. The performance of the method shows that it is effective in estimating the optimal deformation parameters between a pair of fingerprints.

Fingerprint alignment using similarity histogram

The performance of fingerprint matching algorithm relies heavily on the accuracy of fingerprint alignment. Falsely aligning two feature sets extracted from two finger images of a fingerprint will increase the false rejection rate (FRR). In order to improve the performance of fingerprint matching algorithm, we present a new fingerprint alignment algorithm called similarity histogram approach (SHA). First, we calculate the local similarity matrix based on minutiae and associate ridges between two fingerprints. Then, similarity histograms of transformation parameters are constructed from local similarity matrix. In the end, the optimal transformation parameters are obtained using a statistical method. Experimental results on FVC databases show that our method is effective and reliable.

Face Recognition with Relative Difference Space and SVM

In this paper, a new method based on relative difference space (RDS) and support vector machine (SVM) is proposed for multi-class recognition. First the RDS transformation converts the multi-class problem to a binary-class problem, and then SVM is used for the binary classification directly. Compared with the traditional method of difference space (DS), RDS is reversible and it overcomes the ill-transformation problem. This method is applied to face recognition in Yale Face database B, and the recognition result demonstrates its robust performance under different illumination conditions

A fingerprint identification algorithm by clustering similarity

This paper introduces a fingerprint identification algorithm by clustering similarity with the view to overcome the dilemmas encountered in fingerprint identification. To decrease multi-spectrum noises in a fingerprint, we first use a dyadic scale space (DSS) method for image enhancement. The second step describes the relative features among minutiae by building a minutia-simplex which contains a pair of minutiae and their local associated ridge information, with its transformation-variant and invariant relative features applied for comprehensive similarity measurement and for parameter estimation respectively. The clustering method is employed to estimate the transformation space. Finally, multi-resolution technique is used to find an optimal transformation model for getting the maximal mutual information between the input and the template features. The experimental results including the performance evaluation by the 2nd International Verification Competition in 2002 (FVC2002), over the four fingerprint databases of FVC2002 indicate that our method is promising in an automatic fingerprint identification system (AFIS).

Embedded fingerprint identification system based on DSP

Fingerprint recognition is implemented on Ti DSP chip Ti 5402. The algorithm is prompt and practicable. Enhance part adopts a fast orientation filter to improve inputting image quality combining fast orientation interpolation method. On the other hand, the orientation field is used in fingerprint image segment. Matching part uses point match method and combines some post-processing in order to get good match result. One fusion way is introduced in enrollment. In DSP implement phase, the system frame adopts one kind of dispatched system structure aiming at the 5402 features. Otherwise the algorithm of fingerprint recognition is modified and optimized based on DSP instructions. Experiment result indicates that system performance is good.

The toolkit and platform for biometric information processing

A biometric information processing toolkit (BITK) is designed and implemented to support the biometrics research, e.g. algorithm development and performance evaluation. BITK is an object-oriented C++ software development toolkit (SDK), and it provides a consistent, flexible and reusable framework to integrate algorithms, data structures, and visualization methods. In addition, an application platform based on BITK (BITKAPP) is developed. BITKAPP makes the best of BITK to serve the biometrics researchers with its friendly user interface and the plug-in architecture. The meaningful applications of the toolkit and platform confirm that they effectively support the biometrics research.

Improving fingerprint recognition performance based on feature fusion and adaptive registration pattern

This paper proposes an adaptive registration pattern based fingerprint matching method dealing with the non-linear deformations in fingerprint The “registration pattern” between two fingerprints is the optimal registration of every part of one fingerprint with respect to the other fingerprint Registration patterns generated from imposters matching attempts are different from those patterns from genuine matching attempts, although they share some similarities in the aspect of minutiae In this paper, we combine minutiae, associate ridges and orientation fields to determine the registration pattern between two fingerprints and match them The proposed matching scheme has two stages An offline, training stage, derives a genuine registration pattern base from a set of genuine matching attempts Then, an online matching stage registers the two fingerprints and determines the registration pattern A further fine matching is conducted In addition, the block orientation field is used as the global feature of a fingerprint to improve the performance of this method And 2nd and 3rd relational structures between minutiae are applied to promote the fingerprint matching method Experimental results evaluated by FVC2004 demonstrate that the proposed algorithm is an accurate one.