Different data acquisition devices produce images of several gigabytes. Analyzing such large images raises two main issues. First, the data volume to process forbids a global image analysis, hence a difficult partitioning problem. Second, a multi-resolution approach is required to extract global features at low resolution. For instance, regarding histological images, scanners' accuracy recently improved such that cellular structures can be examined on the whole slide. However, produced images are up to 18GB. Besides, considering a tissue as a particular layout of cells is a global information only available at low resolution. Thus, these images combine multi-scale and multi-resolution information. In this work, we define a topological and hierarchical model which is suitable for the segmentation of large images. Our work is based on the previous models of topological map and combinatorial pyramid. We introduce the tiled map model in order to represent large partitions and a hierarchical extension, the tiled top-down pyramid, to represent the duality between multi-scale and multi-resolution information. Finally, we propose an application of our model for the segmentation of large images in histology.
Keywords: Topological model; Combinatorial map; Image processing; Medical imaging; Irregular pyramids; Segmentation
This file was generated by bibtex2html 1.96.