基于小波变换的指纹全局方向场重建

Wavelet transform for global fingerprint orientation field reconstruction

从大型指纹库识别不完整或局部指纹仍然是今天的一大挑战。在此文中,我们研究利用小波变换用于指纹方向场重建问题。特别的,我们提出了一种基于小波的多尺度方法从局部的指纹重建全局拓扑表达。然后提出基于结合参数模型和非参数模型来描述重建问题,我们提供了一般表达式可用于所有有效的反变换模型的解决方案。这种方案允许我们分割保护存在的方向场同时预测丢失的未知部分的结构。我们还开发了基于脊线拓扑特征的一些先验信息来估计丢失的方向结构的算法。我们的统计实验表明我们提出的基于模型的算法能有效的恢复指纹的方向场并应用于指纹匹配,这样重大的提高了局部指纹识别其他模块性能。

Identifying incomplete or partial fingerprints from a large fingerprint database remains a difficult challenge today. In this paper, we investigate the problem of inverse orientation model by exploiting wavelet translation. Specifically, we propose an wavelet based multiscale approach for reconstructing the global topology representation from a partial fingerprint. Then, we present an combine parametric model and non- parametric model for describing the reconstruction problem, we provide a general expression for all valid solutions to the inverse model. This allows us to preserve data fidelity in the existing segments while exploring missing structures in the unknown parts.We have further developed algorithms for estimating the missing orientation structures based on some a priori knowledge of ridge topology features. Our statistical experiments show that our proposed model-based approach can effectively reconstruct the orientation of fingerprint and used for pair-wised fingerprint matching, and thus significantly improve the other system module performance for partial fingerprint identification.