Contactless fingerprint recognition is highly promising and an essential component in the automatic fingerprint identification system. However, due to the inherent characteristic of perspective distortions of contactless fingerprints, achieving a highly accurate contactless fingerprint recognition system is very challenging. In this paper, we propose a robust contactless fingerprint recognition method based on global minutia topology and loose genetic algorithm. In order to avoid the inaccurate minutiae alignment problem suffered in conventional transformation-based methods, the minutiae correspondence is established by optimizing an energy function of the similarity matrix. We define an innovative similarity matrix based on both minutiae and minutia-pairs, which takes the global minutia topology into account. By adopting a distortion-free feature of ridge count to define the similarity, the problem of perspective distortions is effectively overcome. To solve the optimization, we propose a new genetic algorithm (GA) named loose GA with new mutation and crossover operators. We also propose a strict minutia-pair expanding algorithm to enhance the reliability of the minutiae correspondence. For recognition, a metric for measuring comparison scores which takes advantage of both the global topological similarity and the number of corresponding minutiae is proposed. We evaluate our method using two contactless fingerprint benchmark databases and achieve competitive performances in comparison with the state-of-the-art methods.

中文翻译：

---

基于全局细节拓扑和松散遗传算法的非接触式指纹识别


非接触式指纹识别前景广阔，是自动指纹识别系统的重要组成部分。然而，由于非接触式指纹固有的透视扭曲特性，实现高精度的非接触式指纹识别系统非常具有挑战性。在本文中，我们提出了一种基于全局细节拓扑和松散遗传算法的鲁棒非接触式指纹识别方法。为了避免传统基于变换的方法中遇到的细节点对齐不准确的问题，通过优化相似度矩阵的能量函数来建立细节点对应关系。我们基于细节和细节对定义了一个创新的相似性矩阵，它考虑了全局细节拓扑。通过采用脊数的无畸变特征来定义相似度，有效克服了透视畸变的问题。为了解决优化问题，我们提出了一种新的遗传算法（GA），名为松散 GA，具有新的变异和交叉算子。我们还提出了严格的细节对扩展算法来增强细节对应的可靠性。为了识别，提出了一种测量比较分数的度量，该度量利用全局拓扑相似性和相应细节的数量。我们使用两个非接触式指纹基准数据库评估我们的方法，并与最先进的方法相比实现了具有竞争力的性能。