Open AccessAlpha cut for interactive image segmentation of thin and elongated objects
Author(s) -
Tran Nam H.,
Seo Dongsun,
Woo Dongmin,
Won Yongyuk,
Tu Hieu T.
Publication year - 2019
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2018.5740
Subject(s) - cut , segmentation , image segmentation , artificial intelligence , graph , computer vision , computer science , binary number , mathematics , pattern recognition (psychology) , theoretical computer science , arithmetic
Shrinking bias problem is a practical limitation of graph‐cut‐based methods for binary image segmentation. The detail parts with thin elongated object are not well preserved in graph cut minimisation as a result. The authors propose to use structure transferring to overcome the problem with an expanded L2 norm of colour difference. They also show that the structure‐transferring output can be integrated into graph cuts as a counter‐balance to shrinking problem. Experimental results show that the proposed alpha‐cutting technique is effective and efficient in improving segmentation of thin elongated objects.