Exploration of the Vienna City Library Poster Collection using Computer Vision Approaches

Parts of collections of libraries, archives, and e.g. museums can still be uncatalogued. Even if metadata is provided, only standardized information of the described resources (dependent on the collection) is available, i.e., creator names, titles, and subject terms, limiting the search options for experts and typical users. In the case of image-based collections, the information of the image itself can be used as an additional feature to extend the search capabilities of the user. This paper analyzes the use of standard computer vision methods to explore the Vienna City Library poster collection using additional image-based properties. The proposed exploration tool allows a search based on the provided metadata and features based on face detection and retrieval, image retrieval, object detection, text recognition, and main color similarity. The OpenSearch engine is used to index the metadata and visual features, allowing for a real-time search of extensive collections. The qualitative and quantitative analysis shows the potential of visual features within a search tool.