This paper proposes a deep-learning-based approach to writer retrieval and identification for papyri, with a focus on identifying fragments associated with a specific writer and those corresponding to the same image. We present a novel neural network architecture that combines a residual backbone with a feature mixing stage to improve retrieval performance, and the final descriptor is derived from a projection layer. The methodology is evaluated on two benchmarks: PapyRow, where we achieve a mAP of 26.6 % and 24.9 % on writer and page retrieval, and HisFragIR20, showing state-of-the-art performance (44.0 % and 29.3 % mAP). Furthermore, our network has an accuracy of 28.7 % for writer identification. Additionally, we conduct experiments on the influence of two binarization techniques on fragments and show that binarizing does not enhance performance. Our code and models are available to the community.

翻译：本文提出一种基于深度学习的纸莎草作者检索与识别方法，重点解决与特定作者关联的残片以及对应同一图像的残片的识别问题。我们设计了一种新颖的神经网络架构，该架构将残差主干网络与特征混合阶段相结合以提升检索性能，最终描述符源自投影层。该方法在两个基准数据集上进行了评估：在PapyRow数据集上，作者检索和页面检索的平均精度(mAP)分别达到26.6%和24.9%；在HisFragIR20数据集上，实现了44.0%和29.3%的mAP，展现出最优性能。此外，我们的网络在作者识别任务上达到了28.7%的准确率。我们还实验分析了两种二值化技术对残片的影响，结果表明二值化并未提升性能。本文代码与模型已向社区开放。