Explorative hyperbolic-tree-based clustering tool for unsupervised knowledge discovery

Exploring and annotating collections of images without meta-data is a laborious task. Visual analytics and information visualization can help users by providing interfaces for exploration and annotation. In this paper, we show a prototype application that allows users from the medical domain to use feature-based clustering to perform explorative browsing and annotation in an unsupervised manner. For this, we utilize global image feature extraction, different unsupervised clustering algorithms and hyperbolic tree representation. First, the prototype application extracts features from images or video frames, and then, one or multiple features at the same time can be used to perform clustering. The clusters are presented to the users as a hyperbolic tree for visual analysis and annotation.