An Unique Dataset for Christian Sacral Objects Identification

Christian religious monuments, such as cathedrals, chapels and temples are found in many places on our planet. World-famous buildings such as the Notre Dame Cathedral in Paris, Gaudi's Cathedral in Barcelona, and St. Vitus Cathedral in Prague are commonly known, and there are many photographs on the Internet that can be used to build machine learning models to identify them. For little known buildings such as small churches in the Czech-German border region, the number of photographs is already significantly lower and similar approaches cannot be used for identification. Based on these facts, our team has compiled an unique dataset for the identification of the most important elements of Christian sacral buildings such as altars, frescoes, pulpits, etc. which are almost always found in them. Our data set was manually created from several thousand real photographs. This dataset seems to be very usable, e.g., for creating new machine learning models and for identifying objects in sacred objects or the objects themselves. This dataset was created within the framework of the project Information system for medieval monuments in the Czech-Bavarian border area, No. 335, which is co-financed by the European Regional Development Fund and the state budget of the Czech Republic (Cross-border Cooperation Programme Czech Republic - Free State of Bavaria Objective ECA 2014-20).基督教宗教建筑遗迹（Christian religious monuments）广泛分布于全球各地，涵盖大教堂（cathedral）、小礼拜堂（chapel）与教堂（temple）等类型。其中巴黎圣母院大教堂、巴塞罗那高迪大教堂以及布拉格圣维特大教堂等世界知名建筑广为人知，互联网上留存有大量相关照片，可用于构建识别此类建筑的机器学习模型。而诸如捷克-德国边境区域小型教堂这类知名度较低的宗教建筑，其互联网照片数量显著减少，难以通过类似方法实现识别。基于上述现状，本团队构建了一套独特的数据集，用于识别基督宗教圣所建筑中几乎普遍存在的核心元素，包括祭坛（altar）、壁画（fresco）、讲道坛（pulpit）等。本数据集由数千张实拍照片手动采集整理而成，可广泛应用于新型机器学习模型的构建，以及圣所内物品或建筑本体的识别任务。 本数据集的构建依托于编号为335的《捷克-巴伐利亚边境地区中世纪遗迹信息系统》项目，该项目由欧洲区域发展基金与捷克共和国国家预算共同资助，属于「捷克共和国-巴伐利亚自由州跨境合作计划ECA 2014-20」项目范畴。