Premium
Adaptive watershed segmentation of binary particle image
Author(s) -
SUN H.Q.,
LUO Y.J.
Publication year - 2009
Publication title -
journal of microscopy
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.569
H-Index - 111
eISSN - 1365-2818
pISSN - 0022-2720
DOI - 10.1111/j.1365-2818.2009.03125.x
Subject(s) - maxima and minima , spurious relationship , watershed , merge (version control) , segmentation , binary number , artificial intelligence , computer vision , position (finance) , computer science , pattern recognition (psychology) , algorithm , mathematics , mathematical analysis , machine learning , arithmetic , finance , economics , information retrieval
Summary Oversegmentation is a tough problem in the morphological watershed segmentation of irregular‐shaped binary particles, which is usually caused by spurious minima in the inverse distance transform. The position relationship between two objects is clear, according to the value of overlap parameter defined in the paper, and an adaptive algorithm is presented to depress oversegmentation by building the criterion to merge the spurious local minima. Some particle images are provided to validate the performance of the proposed method.