Supervised quality evaluation of binary partition trees for object segmentation

作者：

Highlights：

• The problem of quality assessment of binary partition trees is formalized in the context of object segmentation.

• An approach for supervised quality assessment is proposed based on standard segmentation quality metrics.

• The quality assessment framework is applied in the context of natural image segmentation.

摘要

•The problem of quality assessment of binary partition trees is formalized in the context of object segmentation.•An approach for supervised quality assessment is proposed based on standard segmentation quality metrics.•The quality assessment framework is applied in the context of natural image segmentation.

论文关键词：Binary partition tree,Object segmentation,Hierarchical image model,Supervised quality evaluation,Mathematical morphology

论文评审过程：Received 8 December 2019, Revised 25 July 2020, Accepted 18 September 2020, Available online 22 September 2020, Version of Record 28 September 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107667