Accurate Detection in Volumetric Images using Elastic Registration based Validation
German Conference on Pattern Recognition (GCPR): 453--463, 2014
Abstract: In this paper, we propose a method for accurate detection and segmentation of cells in dense plant tissue of Arabidopsis Thaliana. We build upon a system that uses a top down approach to yield the cell segmentations: A discriminative detection is followed by an elastic alignment of a cell template. While this works well for cells with a distinct appearance, it fails once the detection step cannot produce reliable initializations for the alignment. We propose a validation method for the aligned cell templates and show that we can thereby increase the average precision substantially.
Publisher's link
Images and movies
BibTex reference
@InProceedings{MR14a, author = "D. Mai and J. D{\"u}rr and K. Palme and O. Ronneberger", title = "Accurate Detection in Volumetric Images using Elastic Registration based Validation", booktitle = "German Conference on Pattern Recognition (GCPR)", pages = "453--463", year = "2014", url = "http://lmb.informatik.uni-freiburg.de/Publications/2014/MR14a" }