Images contain very rich information, and digital cameras combined with image processing and analysis can
detect and quantify a range of patterns and processes. The valuable information is however often sparse,
and the ever increasing speed at which data is collected results in data-volumes that exceed the computational
resources available. The HATSID project takes a hierarchical approach to acquisition, analysis, and interpretation
of image data. We develop computationally efficient measurements for data description, confidence-driven
machine learning for determination of interestingness, and a theory and framework to apply intelligent
spatial and temporal information hierarchies, distributing data to computational resources and storage options based
on low-level image features. We will focus our efforts on microscopy data, and work in three specific areas where
image collection results in data volumes difficult to handle with today's computational resources, namely
• large-scale time-lapse experiments exploring the dynamics of cells and drug delivery particles in collaboration with Astra Zeneca
• nanometer-resolution transmission electron microscopy data of in collaboration with Vironova AB
• multi-modal digital pathology data from SciLifeLab Sweden.
We expect the resulting methodologies and frameworks to be highly relevant also for other scientific and industrial applications, including surveillance, predictive maintenance and quality control.