Chunxiao Ren

A novel method of score level fusion using multiple impressions for fingerprint verification

How to improve the performance of an existing biometric system is always interesting and meaningful. In this paper, we present a novel method of score level fusion using multiple enrolled impressions to achieve higher verification accuracy of existing fingerprint systems. The main idea of the method is to build a representation of the biometric reference as a polyhedron by taking into account the matching results of multiple enrolled impressions. The verification step consists in measuring a distance between the centroid of the polyhedron and the acquired image. This novel method outperforms the traditional uni-matcher based scheme over a wide range of FAR and FRR values. The equal error rate of our method is observed to be 2.25%, while that of the uni-matcher is 5.75%.

A Linear Hybrid Classifier for Fingerprint Segmentation

Fingerprint segmentation is the important step of image preprocessing in an automatic fingerprint identification system and usually aimed to exclude background regions to reduce the time of subsequent processing and avoid detecting false features. In this paper, a hybrid algorithm based on linear classifiers for the segmentation of fingerprints is presented. The propose algorithm uses a block-wise classifier to separate foreground and background blocks in the main, and employ a pixel-wise classifier to deal with pixels accurately. In order to evaluate the performance of the new method in comparison to the methods based on other classifiers, experiments are performed on FVC2000 DB2. The average error rate of the hybrid technique is observed to be 0.53%, while that of the label box-based segmentation is 0.80%.

Feature selection for sensor interoperability: A case study in fingerprint segmentation

The need for sensor interoperability has increased tremendously in many fingerprint large-scale application areas such as e-commerce, welfare-disbursement and e-education. However, the problem of feature selection for sensor interoperability has received limited attention in the literature. In this paper, the relationships among person, sensor and feature are discussed. Especially, a feature selection method for sensor interoperability is proposed. Some experimental results of feature selection for sensor interoperability in fingerprint segmentation are presented as a case study. Experiments show that the various features exhibit different sensor interoperability on different sensors.

Fingerprint Scaling

The problem of fingerprint scaling has received limited attention in the literature. Fingerprint scaling is an important issue for fingerprint sensor interoperability. However, no systematic study has been conducted to ascertain its effect on fingerprint systems. In this paper, a fingerprint scaling scheme using the average inter-ridge distance is presented. At first, the average inter-ridge distances of two fingerprint images acquired with two different fingerprint sensors are estimated respectively. Then the images are zoomed according to scale of the two average inter-ridge distances. Experiments have shown that the proposed fingerprint scaling method has good performance.

Fingerprint image segmentation based on linear classifier

Fingerprint segmentation is an important step in automatic fingerprint identification fields. This paper discusses a new method, which is based on a linear classifier, to enhance the performance of fingerprint image segmentation. The novel linear classifier is a label box that is employed to establish a model and deal with fingerprint image quickly and accurately. In order to evaluate the performance of the new method in comparison to the methods based on other linear and nonlinear classifiers, experiments are performed on FVC2000 DB2. The experimental results show the proposed method is able to provide more accurate high-resolution segmentation results than those of previously known ones because only 0.80% of the pixels are misclassified by the method, while the nonlinear classifier, quadric surface classifier, misclassifies 0.97% of the pixels.

A framework of multitemplate ensemble for fingerprint verification

How to improve performance of an automatic fingerprint verification system (AFVS) is always a big challenge in biometric verification field. Recently, it becomes popular to improve the performance of AFVS using ensemble learning approach to fuse related information of fingerprints. In this article, we propose a novel framework of fingerprint verification which is based on the multitemplate ensemble method. This framework is consisted of three stages. In the first stage, enrollment stage, we adopt an effective template selection method to select those fingerprints which best represent a finger, and then, a polyhedron is created by the matching results of multiple template fingerprints and a virtual centroid of the polyhedron is given. In the second stage, verification stage, we measure the distance between the centroid of the polyhedron and a query image. In the final stage, a fusion rule is used to choose a proper distance from a distance set. The experimental results on the FVC2004 database prove the improvement on the effectiveness of the new framework in fingerprint verification. With a minutiae-based matching method, the average EER of four databases in FVC2004 drops from 10.85 to 0.88, and with a ridge-based matching method, the average EER of these four databases also decreases from 14.58 to 2.51.

Video-based fingerprint verification

In this paper, fingerprint videos are used to improve the accuracy of a fingerprint verification system. We define the “inside-similarity” and “outside-similarity” to represent the similarity within a video and between two videos, respectively. A new method is proposed to define and calculate the matching score of two videos according to the similarity and the effect on the error probability of this method is analyzed theoretically. Experimental results confirm our arguments in the analysis and indicate that the proposed method can lead a much better performance than the method using a single impression. Therefore, we believe that video-based method is an effective approach to improve the accuracy of fingerprint system.

A performance improvement method for existing fingerprint systems

How to improve the performance of an existing fingerprint system is an interesting and meaningful problem. Considering the widespread deployment of fingerprint systems, the performance improvement method is very practical and instructive to not only the existing fingerprint systems but also the next biometric systems. In this paper, we propose a novel performance improvement method based on fingerprints Mobius representation and Choquet integral for an existing fingerprint system. The basic idea of our method is to map the fingerprint similarity as a distance in a geometric space firstly, and then transform the similarity problem between the impressions into a geometric problem through using multiple impressions, and last, map the results obtained in geometric space back to solve the fingerprint similarity problem. The experiments show that the performance achieved by using this method is better than that of other methods.