Zhongchao Shi

A new segmentation algorithm for low quality fingerprint image

Aiming at the segmentation of low quality fingerprint images, a new framework, which is different from traditional methods that usually use some certain features to segment diversified images, is proposed. There are two contributions in this scheme: firstly, we introduce a quality estimation step before segmentation, which can remove a great many false traces effectively; secondly, a new feature eccentric moment is proposed to locate the blurry boundary. Then we segment the image using the new block feature of clarified image. Experimental results show that the proposed method can segment low quality fingerprint images properly.

A Robust Fingerprint Matching Method

This paper is concerned with an accurate and efficient fingerprint matching method. We have two main contributions: 1. we define a novel feature vector for each fingerprint minutia based on the global orientation field estimated from the fingerprint impression. These features are used to identify corresponding minutiae between two fingerprint impressions by computing the Euclidean distance between these feature vectors. 2. a novel distortion-tolerant matching algorithm based on the closest triangle is developed. Furthermore, the fingerprint directional field is also used to compute the final matching score combining with minutiae elaborately. A series of experiments conducted on the public data collection, FVC2002 DB3 set A (800 fingerprints), demonstrates the effectiveness of our method.

A new fingerprint image segmentation algorithm based on ROI

We present a new fast and effective method of fingerprint image segmentation, which is different from traditio-nal methods that usually use some certain features to segment diversified images. Based on the region of inte-rest, an approach is introduce, which is specialized on preprocessing a certain kind of bad fingerprint images with a great many blurs, false traces and sweat spots. It just mimics the way of finding region of interest by human beings and locating the area of low intensities quickly. Experimental result shows a significant improve-ment in fingerprint segmentation performance.

Cascading a couple of registration methods for a high accurate fingerprint verification system

As far as we know, although various approaches of combining multiple fingerprint matchers have been proposed in the literature, no previous attempts to combine multiple fingerprint registration algorithms have been tried In this paper, we have presented a novel registration algorithm by cascading a couple of different registration techniques to improve the accuracy of fingerprint matching system A series of experiments conducted on the public data collection, FVC2002 DB3 set A (800 fingerprints), demonstrates the effectiveness of our method.

Measuring fingerprint image quality using gradient

In an automatic fingerprint identification system, image enhancement step and match component can benefit from the estimation of fingerprint image quality. In this paper, a criterion for fingerprint image quality is established based on the gradient of fingerprint image. We test the quality measuring method using the proposed criterion on the fingerprint image database, DB3 in FVC2002. From the experimental results , it can be shown that the method is available for estimating the fingerprint image quality.

An Integration of Topographic Scheme and Nonlinear Diffusion Filtering Scheme for Fingerprint Binarization

This paper proposes an approach to fingerprint binarization integrating nonlinear diffusion filtering scheme and topographic scheme in which the properties of essential flow-like patterns of fingerprint are deliberately analyzed in different points of view. The filtering scheme is on the basis of the the coherent structures, while the topographic scheme is based on the analysis of the underlying 2D surface. The fingerprint image is smoothed along the coherent structures and binarized according to the sign of the trace of the Hessian matrix. The integration method is tested with a series of experiments and the results reveal the good performance of our algorithm.

A study of minutiae matching algorithm based on orientation validation

In this paper, we promote a new fingerprint minutia matching algorithm based on orientation validation Firstly, we use 1 Nearest Neighbor of the minutiae local structure to find some corresponding point pairs and get the best one by clustering Secondly, A structure matching algorithm is used to match the global minutiae, and a matching table is used to avoid multi-minutiae match to one minutia and vice versa Moreover, we promote a new decision method based on orientation validation, and a new rule is proposed to make the final judgment Finally, the experimental results conducted in DB3, from FVC2002, show that the performance of our algorithm is good.

Fingerprint Matching Integrating the Global Orientation Field with Minutia

We define a novel structure for each minutia in the fingerprint based on the global orientation field. Then the structure pattern is used to establish the minutia correspondence between the test fingerprint and template fingerprint. A new technique calculating the matching score is developed based on both the number of corresponding minutia pairs and the similarity level between the template fingerprint orientation field and the aligned test fingerprint orientation field. The results of the experiment conducted on the public data collection, DB3, demonstrate the effectiveness of the method in this paper.