TY - JOUR
T1 - Ensemble segmentation using efficient integer linear programming
AU - Alush, Amir
AU - Goldberger, Jacob
PY - 2012/10
Y1 - 2012/10
N2 - We present a method for combining several segmentations of an image into a single one that in some sense is the average segmentation in order to achieve a more reliable and accurate segmentation result. The goal is to find a point in the "space of segmentations" which is close to all the individual segmentations. We present an algorithm for segmentation averaging. The image is first oversegmented into superpixels. Next, each segmentation is projected onto the superpixel map. An instance of the EM algorithm combined with integer linear programming is applied on the set of binary merging decisions of neighboring superpixels to obtain the average segmentation. Apart from segmentation averaging, the algorithm also reports the reliability of each segmentation. The performance of the proposed algorithm is demonstrated on manually annotated images from the Berkeley segmentation data set and on the results of automatic segmentation algorithms.
AB - We present a method for combining several segmentations of an image into a single one that in some sense is the average segmentation in order to achieve a more reliable and accurate segmentation result. The goal is to find a point in the "space of segmentations" which is close to all the individual segmentations. We present an algorithm for segmentation averaging. The image is first oversegmented into superpixels. Next, each segmentation is projected onto the superpixel map. An instance of the EM algorithm combined with integer linear programming is applied on the set of binary merging decisions of neighboring superpixels to obtain the average segmentation. Apart from segmentation averaging, the algorithm also reports the reliability of each segmentation. The performance of the proposed algorithm is demonstrated on manually annotated images from the Berkeley segmentation data set and on the results of automatic segmentation algorithms.
KW - EM algorithm
KW - Image segmentation
KW - correlation clustering
KW - ensemble segmentation
KW - integer linear programming
UR - http://www.scopus.com/inward/record.url?scp=84865339430&partnerID=8YFLogxK
U2 - 10.1109/tpami.2011.280
DO - 10.1109/tpami.2011.280
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
C2 - 22213764
AN - SCOPUS:84865339430
SN - 0162-8828
VL - 34
SP - 1966
EP - 1977
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
IS - 10
M1 - 6122028
ER -