This paper presents a novel application of pattern recognition to the provenance classification of archaeological ceramics. This is a challenging problem for archaeologists, which involves assigning a making location to a fragment of archaeological pottery that was found along with other fragments of pieces made in different distant locations from the find. The pieces look very similar to each other and, often, other contextual information about the use of the pieces cannot be used due to the small size of the fragments. Current standard methods to solve this problem are limited since they are time consuming, require costly equipment, and can lead to the destruction of a part of the pieces. The proposed method overcome those limitations using non-destructive ultrasonic testing and incorporates versatile data analysis through advanced pattern recognition techniques. Those techniques include the following: feature ranking, sample augmentation, semi-supervision based on active learning; and optimal fusion. This latter is based in the concept of alpha integration, which allows optimal fitting of the fusion model parameters. Different provenance classification problems are showcased: provenance classification of terra sigillata ceramic pieces from Aretina, Northern Italy and Sud-Gaul origins; and provenance classification of Iberian ceramic pieces from archaeological sites of Paterna, and Les Jovaes in Valencia, Spain. We demonstrate that the proposed fusion-based method achieves the best results, in terms of balanced classification accuracy and F1 score, compared with competitive methods like linear discriminant analysis, random forest, and support vector machine. Experiments for simulating small sample sizes and uncertainty in labeling of the pieces are included. In addition, the paper provides a design of a practical specialized device that could be used in different applications of archaeological ceramic classification.

本文提出了一种模式识别在考古陶瓷物源分类中的新应用。对于考古学家而言，这是一个具有挑战性的问题，涉及将制造地点分配给发现的考古陶器碎片，以及在与发现地点不同距离的地方制作的其他碎片。这些片段看起来彼此非常相似，并且由于片段的小尺寸，常常无法使用有关片段使用的其他上下文信息。当前解决该问题的标准方法受到限制，因为它们很费时间，需要昂贵的设备，并且可能导致零件的损坏。所提出的方法克服了使用无损超声测试的局限性，并通过先进的模式识别技术结合了多种数据分析功能。这些技术包括：特征排名，样本扩充，基于主动学习的半监督；和最佳融合。后者基于alpha积分的概念，该积分允许对融合模型参数进行最佳拟合。展示了不同的出处分类问题：来自意大利北部阿雷蒂纳和Sud-Gaul起源的terra sigillata陶瓷件；特纳（Paterna）和西班牙巴伦西亚（Les Jovaes）考古遗址的伊比利亚陶瓷件的来源和来源分类。我们证明，与线性判别分析，随机森林和支持向量机等竞争性方法相比，基于融合的方法在平衡的分类精度和F1得分方面达到了最佳结果。包括用于模拟小样本尺寸和不确定性的实验。此外，本文提供了一种实用的专用设备的设计，该设备可用于考古陶瓷分类的不同应用。