iART: An interactive analysis- and retrieval-tool for the support of image-oriented research processes

项目“iART：一种支持以图像为导向的研究过程的交互式分析和检索工具”致力于为人文科学的数字化、以图像为导向的研究过程开发一个电子研究工具。它不仅旨在提高图像数据库的检索效率，而且为图像数据的分析提供了各种工具，从而加强了科学工作，促进了新理论的形成。该项目的动机源于比较方法在艺术史上的根本重要性，该方法以图片的相似性为目标，并伴随着当代科学哲学中相似思维的复兴。工具iart旨在将艺术史理论家和比较分析实践者的方法转移到数字时代，并借助现代信息技术将其延伸。在iART的帮助下，基于相似性的图像分析将转移到数字图像库，在很大程度上实现自动化，并得到各种额外功能的补充。基于机器学习的自动模式识别将在这方面发挥核心作用，特别是在用元数据标注图像方面。这一功能将得到图像检索(基于关键字和基于内容)、类别形成(通过集群)以及基于用户行为和反馈的个性化工具的补充。图形界面将支持用户查询以及结果的呈现，例如图像排名(作为检索任务的答案)和集群结构。IART将通过互联网提供，可在普通浏览器上使用，并可通过标准化界面转移到其他数据库。作为一种电子研究工具，它将显著提高人文领域图像化研究的效率，从而支持理论形成和引发新的研究问题。

The project "iART: An interactive analysis- and retrieval-tool for the support of image-oriented research processes" is devoted to the development of an e-Research-Tool for digitized, image-oriented research processes in the humanities and cultural sciences. It not only aims to improve the efficiency of retrieval in image databases but also offers various tools for analyzing image data, thereby enhancing scientific work and facilitating new theory formation. The motivation for the project stems from the fundamental importance of the comparative approach in art history, which targets the similarity of pictures and comes along with a rehabilitation of similarity thinking in contemporary philosophy of science. The tool iART is supposed to transfer the approach of art history theorists and practitioners of Comparative Analysis to the digital age, and to extend it by virtue of modern information technology. With the help of iART, the similarity-based analysis of images will be transferred to digital image repositories, automated to a large extent, and complemented by various additional functionalities. Automated pattern recognition based on machine learning will play a central role in this regard, especially for annotating images with metadata. This functionality will be complemented by tools for image retrieval (both keyword- and content-based), category formation (via clustering), as well as personalization based on user behavior and feedback. User queries as well as the presentation of results such as rankings of images (as an answer to a retrieval task) and clustering structures will be supported by a graphical interface. iART will be made available through the Internet, utilizable with common browsers, and transferable to other databases thanks to standardized interfaces. As an e-Research-Tool, it will significantly improve the efficiency of image-oriented research in the humanities, thereby supporting theory formation and triggering new research questions.