In machine learning applications, it is common practice to feed as much information as possible. In most cases, the model can handle large data sets that allow to predict more accurately. In the presence of data scarcity, a Few-Shot learning (FSL) approach aims to build more accurate algorithms with limited training data. We propose a novel end-to-end lightweight architecture that verifies biometric data by producing competitive results as compared to state-of-the-art accuracies through Few-Shot learning methods. The dense layers add to the complexity of state-of-the-art deep learning models which inhibits them to be used in low-power applications. In presented approach, a shallow network is coupled with a conventional machine learning technique that exploits hand-crafted features to verify biometric images from multi-modal sources such as signatures, periocular region, iris, face, fingerprints etc. We introduce a self-estimated threshold that strictly monitors False Acceptance Rate (FAR) while generalizing its results hence eliminating user-defined thresholds from ROC curves that are likely to be biased on local data distribution. This hybrid model benefits from few-shot learning to make up for scarcity of data in biometric use-cases. We have conducted extensive experimentation with commonly used biometric datasets. The obtained results provided an effective solution for biometric verification systems.

翻译：在机器学习应用中，通常的做法是尽可能多地输入信息。在大多数情况下，模型能够处理大规模数据集，从而实现更精确的预测。当面临数据稀缺时，小样本学习（Few-Shot Learning，FSL）方法旨在利用有限的训练数据构建更精确的算法。我们提出了一种新颖的端到端轻量级架构，该架构通过小样本学习方法验证生物特征数据，并产生与最先进精度相媲美的竞争性结果。当前最先进的深度学习模型中的密集层增加了其复杂度，从而使其难以应用于低功耗场景。在所提出的方法中，我们采用浅层网络结合传统机器学习技术，利用手工设计的特征对来自多模态源（如签名、眼周区域、虹膜、人脸、指纹等）的生物特征图像进行验证。我们引入了一种自估计阈值，该阈值严格监控误接受率（False Acceptance Rate，FAR），同时对其结果进行泛化，从而消除了ROC曲线中可能因局部数据分布而产生偏差的用户定义阈值。这种混合模型受益于小样本学习，以弥补生物特征应用场景中的数据稀缺问题。我们使用常用的生物特征数据集进行了大量实验。所得结果为生物特征验证系统提供了一种有效的解决方案。