TY - JOUR
T1 - Image Segmentation via Probabilistic Graph Matching
AU - Heimowitz, Ayelet
AU - Keller, Yosi
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/10
Y1 - 2016/10
N2 - This paper presents an unsupervised and semi-automatic image segmentation approach where we formulate the segmentation as an inference problem based on unary and pairwise assignment probabilities computed using low-level image cues. The inference is solved via a probabilistic graph matching scheme, which allows rigorous incorporation of low-level image cues and automatic tuning of parameters. The proposed scheme is experimentally shown to compare favorably with contemporary semi-supervised and unsupervised image segmentation schemes, when applied to contemporary state-of-the-art image sets.
AB - This paper presents an unsupervised and semi-automatic image segmentation approach where we formulate the segmentation as an inference problem based on unary and pairwise assignment probabilities computed using low-level image cues. The inference is solved via a probabilistic graph matching scheme, which allows rigorous incorporation of low-level image cues and automatic tuning of parameters. The proposed scheme is experimentally shown to compare favorably with contemporary semi-supervised and unsupervised image segmentation schemes, when applied to contemporary state-of-the-art image sets.
KW - Image segmentation
KW - inference algorithms
KW - machine learning
KW - semisupervised learning
KW - statistical learning
KW - unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=84985946041&partnerID=8YFLogxK
U2 - 10.1109/TIP.2016.2590832
DO - 10.1109/TIP.2016.2590832
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:84985946041
SN - 1057-7149
VL - 25
SP - 4743
EP - 4752
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
IS - 10
M1 - 7511662
ER -