Knowledge Extraction for High-Throughput Biological Imaging

We present a multilayered architecture and spatiotemporal models for searching, retrieving, and analyzing high-throughput biological imaging data. The analysis is divided into low-and high-level processing. At the lower level, we address issues like segmentation, tracking, and object recognition, and at the high level, we use finite state machine-and Petri-net-based models for spatiotemporal event recognition.