Modified Principal Curves Based Fingerprint Minutiae Extraction and Pseudo Minutiae Detection

Zhang, Hongyun; Miao, Duoqian; Zhong, Chongquan

doi:10.1142/s0218001411009135

Cited by 8 publications

(2 citation statements)

References 16 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…31 Because of their initial importance in forensics and the recent need for automated biometric identi¯cation systems, automatic¯ngerprint identi¯cation systems (AFIS) have been studied extensively and are still an highly active research topic. 5,25,37,46 As a result, many wellengineered methods have been proposed for the di®erent stages that encompass such a system (Fig. 1).…”

Section: Introductionmentioning

confidence: 99%

Fingerprint Image Segmentation Using Data Manifold Characteristic Features

Paiva

Taşdizen

2012

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

Automatic¯ngerprint identi¯cation systems (AFIS) have been studied extensively and are widely used for biometric identi¯cation. Given its importance, many well-engineered methods have been developed for the di®erent stages that encompass those systems. The¯rst stage of any such system is the segmentation of the actual¯ngerprint region from the background. This is typically achieved by classifying pixels, or blocks of pixels, based on a set of features. In this paper, we describe novel features for¯ngerprint segmentation that express the underlying manifold topology associated with image patches in a local neighborhood. It is shown that ngerprint patches seen in a high-dimensional space form a simple and highly regular circular manifold. The characterization of the manifold topology suggests a set of optimal features that characterize the local properties of the¯ngerprint. Thus,¯ngerprint segmentation can be formulated as a classi¯cation problem based on the deviation from the expected topology. This leads to features that are more robust to changes in contrast than mean, variance and coherence. The superior performance of the proposed features for¯ngerprint segmentation is shown in the eight datasets from the 2002 and 2004 Fingerprint Veri¯cation Competitions.

show abstract

Section: Introductionmentioning

confidence: 99%

Fingerprint Image Segmentation Using Data Manifold Characteristic Features

Paiva

Taşdizen

2012

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…Verification fingerprint technique can roughly be categorized into two types. The first one is minutia based identification method which adopts the minutia point as the feature of fingerprint [1,2,3,4,5]. The second one is texture-based method that directly extracts the texture information from the global fingerprint image [6,7,8,9,10,11,12].…”

Section: Introductionmentioning

confidence: 99%

Fingerprint Verification Using Weighted Zernike Moments and Fast Computation Based on Multi-disc ROI

Li¹,

Li²,

Da³

2012

JDCTA

View full text Add to dashboard Cite

A texture-based method for fingerprint verification is proposed based on weighted Zernike moments. Zernike moment features are calculated from the region of interest (ROI) which consists of several concentric discs, called multi-discs. Zernike moments of multi-disc ROI are weighted according to the regions of discs. In order to reduce the computational complexity of Zernike moments, the fast Zernike moments algorithm is exploited according the structure of multi-discs. The proposed method is rotation and scale invariant, and it is also robust even the reference point locates in the corner of input image. The experiments results show the proposed method has high verification accuracy than most of the state-of-the-art texture-based methods.

show abstract