Extraction of neurons from images of mouse brain slices based on automated selection of connected morphological filters

Authors:
I. Gurevich;A. Myagkov;A. Nedzved';V. Yashina
Affiliations:
Dorodnicyn Computing Center, Russian Academy of Sciences, Moscow, Russia 119333;Dorodnicyn Computing Center, Russian Academy of Sciences, Moscow, Russia 119333;Joint Institute for Informatics Problems, National Academy of Sciences of Belarus, Minsk, Belarus;Dorodnicyn Computing Center, Russian Academy of Sciences, Moscow, Russia 119333
Venue:
Pattern Recognition and Image Analysis
Year:
2011

Citing 8
Cited 0

Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations

IEEE Transactions on Pattern Analysis and Machine Intelligence
Morphological Image Analysis: Principles and Applications

Morphological Image Analysis: Principles and Applications
Levelings, Image Simplification Filters for Segmentation

Journal of Mathematical Imaging and Vision
A Lattice Approach to Image Segmentation

Journal of Mathematical Imaging and Vision
Information technology for the morphological analysis of the lymphoid cell nuclei

SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
Automating extraction and analysis of dopaminergic axon terminals in images of frontal slices of the striatum

Pattern Recognition and Image Analysis
Levelings and Flat Zone Morphology

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
Flat zones filtering, connected operators, and filters by reconstruction

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe the results of a study on creating an algorithm for automated selection of connected morphological filters to solve image segmentation problems. We propose a similarity measure for image partition. It is used to select the best filters from given families of connected morphological filters in such a way that partition obtained by applying the watershed-segmentation algorithm to a filtered image has the maximum similarity value with the given partition. This method is used to extract neurons from images of mouse brain slices. Experimental research has confirmed that this method is applicable for automated processing and analysis of slice images.