TY - JOUR
AU1 - Yu, Qian
AU2 - Yang, Chengzhuan
AU3 - Fan, Honghui
AU4 - Zhu, Hongjin
AU5 - Ye, Feiyue
AU6 - Wei, Hui
AB - Many state-of-the-art shape features have been proposed for the shape recognition task. In this paper, to explore whether a shape feature influences object segmentation, we propose a specific shape feature, Fisher shape (a form of bag of contour fragments), and we combine this with the appearance feature with multiple kernel learning to create a pipeline of object segmentation system. The experimental results on benchmark datasets clearly demonstrate that the pipeline of object segmentation is effective and that the Fisher shape can improve object segmentation with only the appearance feature.
TI - Bag of contour fragments for improvement of object segmentation
JF - Applied Intelligence
DO - 10.1007/s10489-019-01525-1
DA - 2019-07-16
UR - https://www.deepdyve.com/lp/springer-journals/bag-of-contour-fragments-for-improvement-of-object-segmentation-WFTtGKf5ZE
SP - 203
EP - 221
VL - 50
IS - 1
DP - DeepDyve
ER -